Large Language Model Hallucination

Diffusion models have emerged as the backbone of modern generative AI, powering advances in vision, language, audio and other modalities. Despite their success, they suffer from hallucinations, implausible samples that lie outside the support of true data distribution, which degrade reliability and trust. In this work, we first empirically confirm previously proposed hypothesis that score smoothness causes hallucinations in Image Generation diffusion models and provide a density-based perspective. We further formalize this notion by linking the hallucinations probability mass to lipschitz constant of the learned score function. Motivated by this, we introduce a Variance-Guided Score Modulation (VSM) strategy that controls the score Jacobian, in turn reducing score smoothness and better approximating the ground truth score that decreases hallucinations. Empirical results on synthetic and real-world datasets demonstrate that our approach reduces hallucinations (up to ~25%) while maintaining high fidelity and diversity, providing a principled step toward more reliable diffusion-based image generation. We also propose two benchmark datasets with extreme semantic variation for systematic hallucination evaluation. Code and Datasets are publicly available at https://github.com/bhosalems/VSM.

Contrastive decoding (CD) seeks to mitigate hallucinations in Large Vision-Language Models (LVLMs) by contrasting the output distributions of a standard model and a visually degraded model. However, existing training-free CD methods suffer from sub-optimal degraded branches: completely dropping visual tokens is too extreme and induces language hallucinations, while corrupting input images offers coarse control over visual evidence and suffers from high inference latency due to requiring two full forward passes. To address these dilemmas, we propose YARD, a training-free Y-Architecture Register Decoding framework. Motivated by the observation that reliable text-to-vision grounding predominantly emerges in the middle decoder layers, YARD constructs the degraded branch internally by sharing shallow-layer computations and branching exactly at this critical stage. For the degraded branch, YARD replaces patch-level visual tokens with register tokens, which preserve global image semantics but lack fine-grained local evidence. This image-aware yet locally under-grounded design provides a faithful contrastive signal without extreme modality mismatch, while the Y-architecture strictly avoids a costly second forward pass. Extensive experiments on generative and discriminative hallucination benchmarks demonstrate that YARD consistently achieves state-of-the-art hallucination mitigation across multiple LVLMs, alongside a significant reduction in inference latency.

Multimodal hallucination remains a persistent challenge for Vision-Language Models (VLMs). Standard textual Direct Preference Optimization (DPO) often fails to mitigate it due to a lack of explicit visual supervision. While existing works introduce visual preference DPO by contrasting original images against negative ones, they suffer from a theoretically inconsistent objective caused by partition function mismatches and rely on coarse-grained negatives that could enable shortcut learning. In this work, we propose In-Context Visual Contrastive Optimization (IC-VCO). By placing contrastive images within a shared multi-image context, IC-VCO ensures a mathematically rigorous objective. We further introduce Visual Contrast Distillation (VCDist), an auxiliary reliability-gated regularizer that encourages consistency between multi-image contrastive training and single-image inference. Finally, we propose a contrastive sample editing strategy that generates hard negatives via precise semantic perturbations. Experiments on five benchmarks demonstrate IC-VCO's best overall performance and the effectiveness of our sample editing strategy. Code and data are available at https://github.com/OPPO-Mente-Lab/IC-VCO.

Hallucination remains one of the key challenges undermining the reliability of Large Vision-Language Models (LVLMs). But what makes an LVLM hallucinate less? Many existing efforts focus on improving internal components of the model. We argue that hallucination fundamentally stems from how the model architecture is designed. To investigate this, we factor the architecture design into three dimensions: Linguistic Foundation (LF), Visual Representation (VR), and Semantic Alignment (SA), and categorize hallucinations into Co-occurrence, Similarity, and previously overlooked Uncertainty types. Building on this formulation, we propose CoSimUE, a benchmark that creates fine-grained hallucination scenarios through controlled textual perturbations and random perturbations, enabling mapping between design choices and hallucination behaviors. Experiments across 7 design aspects show that: 1) the widely emphasized scaling of model parameters has only limited impact on reducing all three types of hallucinations; 2) larger and better-trained language foundations can reduce co-occurrence hallucinations; 3) stronger visual encoders and higher resolutions mitigate similarity errors; 4) effective alignment strategies alleviate uncertainty hallucinations. 5) Furthermore, cross-dimensional analysis reveals that jointly enhancing visual fidelity and alignment quality yields the most comprehensive improvements. This study provides the first systematic exploration linking architecture-level design to hallucination robustness, offering practical guidance for developing reliable and efficient LVLMs.

LLM-powered coding agents increasingly participate in software development workflows by generating code, selecting dependencies, and producing package installation commands. This creates a new software supply chain risk: when an agent hallucinates a non-existent package, an attacker may register the hallucinated name and later compromise users who install it. Existing package hallucination attacks and defenses primarily focus on naturally occurring hallucinations, targeted dependency steering, or post-hoc package validation. In this paper, we introduce \emph{Neutral Prompting Attack} (NPA), a highly stealthy attack paradigm in which semantically benign instructions, such as encouraging imagination and exhaustiveness, increase package hallucination propensity without containing explicit malicious intent. Unlike targeted dependency steering, NPA does not specify an attacker-chosen package. Instead, it shifts the model's dependency generation behavior toward more speculative package names. We evaluate NPA across multiple coding-oriented LLMs and package hallucination benchmarks. Our results show that NPA increases both \emph{Hallucination ASR} and \emph{Pip Install ASR}, changes the distribution of hallucinated package names, and evades existing static-analysis, LLM-based, and agent-based Skill defenses. These findings reveal that harmless-looking prompts can covertly manipulate hallucination behavior and create downstream software supply chain risks.

Large language models (LLMs) have shown promise on summarization tasks, but they often produce hallucinations, which are unsupported or incorrect statements that limit their reliability in specialized healthcare applications. We introduce Hallucination Detection Guided Self-Refinement (HDSR), an inference-time method that leverages hallucination detectors to guide iterative summary revisions toward factual corrections. Building on this, we propose HDSR for Preference Learning (HDSR-PL), which converts detector-guided refinement trajectories into preference pairs for model finetuning. Extensive experiments show that our methods substantially reduce hallucinations for Llama and Gemma models in summarizing real-world clinical notes from MIMIC-IV-Note v2.2. For example, HDSR reduces 24% and HDSR-PL reduces 48% hallucinations in Llama-3.1-8B-Instruct. Importantly, both methods preserve summary fluency, coherence, and relevance according to human expert and LLM-Jury evaluations. Together, these results demonstrate that detection-informed refinement and preference learning offer an automated solution for improving factual faithfulness in clinical summarization.

Prompt-based verification is widely used to mitigate hallucinations in large vision-language models (LVLMs), yet when it helps remains poorly understood. We systematically study verification prompting across two representative LVLM architectures and hallucination benchmarks, and find that it is a risk-bearing intervention: its corrections increase with input difficulty, while newly introduced errors persist across difficulty levels. As a result, always-on prompting helps on hard inputs but offers little benefit -- and can harm -- easier ones. Our analysis further shows that this behavior is associated with a conservative output shift. Verification prompts redistribute attention from visual tokens toward instruction tokens and induce a distinct middle-layer entropy pattern absent in a neutral-prompt control, suggesting instruction-conditioned attention redistribution rather than uniformly improved visual grounding. Motivated by this input-dependent risk, we propose Risk-aware Selective Prompting (RSP), a training-free approach that uses pre-generation uncertainty signals to trigger verification selectively. RSP mitigates the degradation of always-on prompting while preserving baseline performance, and reveals that effective selection signals vary across architectures.

Retrieval-Augmented Generation (RAG) mitigates LLM hallucinations but introduces a critical vulnerability: corpus integrity. We present SilentRetrieval, a two-stage data poisoning attack that hijacks RAG systems through adversarially crafted yet fluent documents. Stage 1 uses Coordinated Beam Search, a multi-token joint optimization method with a fluency-similarity objective, to keep a poisoned host document retrievable while constraining perplexity. Stage 2 uses Context-Adaptive Trigger Generation, a lightweight trigger-fusion step driven by a frozen LLM, to integrate manipulation triggers into document content. Under a one-poisoned-document-per-query evaluation with synthetic target answers, SilentRetrieval achieves 84.6%/81.3% HR@10 and 57.5%/54.8% ASR-LLM on Natural Questions and MS MARCO, while maintaining near-benign perplexity. Cross-model evaluation across four target LLMs shows nontrivial effectiveness under a fixed trigger generator, and transfer tests against unseen retrievers, including ColBERT and commercial embedding models, yield 64.7% average HR@10 under the same injected-corpus protocol. In a sampled Wikipedia-scale evaluation, SilentRetrieval retains 74.2% HR@10 at a 0.016% poisoning ratio. Combined retrieval-side and generation-side defenses reduce attack success substantially but incur a latency trade-off. Human evaluation shows substantially lower flag rates than disfluent baselines, while remaining numerically more suspicious than benign content at the current sample size.

Object hallucination remains a primary obstacle to the reliable deployment of Multimodal Large Language Models (MLLMs). Current inference-time mitigation methods mainly assume hallucinations stem from visual neglect, steering models to enhance visual reliance. In contrast, our systematic interventions on multiple MLLMs show that pushing toward more visual reliance may exacerbate hallucinations on some models, while less may mitigate hallucinations. This result suggests that attributing hallucinations solely to visual insufficiency is underdetermined. We argue that the image, as a context, simultaneously competes with the model's parametric knowledge and the textual context. For this, we propose a training-free framework, Context-Preference Activation Steering (CAS). It extracts two semantically distinct Context Preference Vectors (CPVs) via two small sets of designed conflict samples and applies them via single-pass signed residual injection at mid-early MLP layers during inference to control information reliance. Experiments show that CAS substantially mitigates object hallucinations without increasing decoding latency and preserves native text-generation quality.

Multimodal Large Reasoning Models introduce the reasoning paradigm, demonstrating strong capabilities on complex vision-language tasks. However, they still suffer from severe hallucinations. Existing training-based methods typically mitigate hallucinations through response-level direct preference optimization (DPO), where the Chain-of-Thought (CoT) and the final answer are treated as a monolithic output and optimized jointly. We reveal that this formulation performs similarly to answer-only optimization, suggesting that it primarily learns answer-level preference, while leaving CoT-level supervision insufficiently exploited. To address this issue, we explicitly formulate a CoT-oriented preference term and derive Reasoning-Conditioned Direct Preference Optimization (RC-DPO), which models the CoT as a condition for answer generation and contrasts the preference for the same preferred answer under different CoT conditions, promoting answer-supportive reasoning chain alignment. To further improve optimization, we introduce a reasoning-enhanced preference data generation strategy that employs Monte Carlo Tree Search to discover visually grounded and logically consistent CoTs as positive samples, and attention-guided CoT token pruning to construct negative ones. Extensive experiments across various models and benchmarks show that RC-DPO effectively mitigates hallucinations and improves the reliability of the multimodal reasoning process.

We introduce CAROL (Chain-based Adaptive Reconfiguration Over Lattices), a probabilistic framework for test-time hallucination reduction in large language models. Rather than relying on token-level uncertainty, CAROL defines a semantic uncertainty measure based on the consistency between generated responses and a trusted context, inducing a string-submodular objective over a lattice of textual sequences. This formulation enables hallucination mitigation to be cast as a Markov chain accept-reject process with provable convergence and near-optimality guarantees, allowing the model to iteratively refine outputs toward semantic consistency. By operating at the level of meaning, CAROL unifies hallucination detection and mitigation within a single framework. Empirical results on question answering and multi-agent reasoning benchmarks show that CAROL significantly reduces hallucinations and improves reliability and interpretability compared to likelihood-based and retrieval-augmented baselines, while maintaining competitive computational efficiency.

Recently, there has been increased interest in Small Language Models (SLMs), which are fast, show good performance, and have lower hardware demands than large language models (LLMs). However, SLMs hallucinate more frequently than LLMs, impacting their ability to solve complex multi-step reasoning problems as early mistakes cascade to the final response. To address this, existing works think-first followed by iterative retrieval to reduce hallucination. We argue that the think-first strategy is not always necessary as we find that: (i) SLMs are often accurately confident in their initial answer and, (ii) hallucinations can actually be beneficial for honing in on the true answer. As such, we position our work as an inversion of this strategy, i.e., answer first-reason later. We propose a cognitively-inspired framework where the model is first allowed to quickly answer the question (System-I (zero-shot)) and then resorts to deeper thinking (System-II) based on evidence retrieved from a knowledge source using the initial hypothesis. By combining System-I and System-II style thinking, we show that our method can outperform prior work that takes the traditional think-first route on various multi-step question-answering benchmarks.

Large Language Models (LLMs) are being rapidly adopted in agricultural imaging applications, ranging from crop interpretation to synthetic field image generation. However, these models frequently exhibit hallucinations outputs that appear confident yet deviate from biological or environmental reality potentially leading to misinformed agronomic insights. This study investigates such hallucinations in two complementary directions: image-to-text, where LLMs interpret crop or field imagery to describe conditions such as biotic and abiotic stresses, and text-to-image, where models generate synthetic agricultural scenes based on descriptive prompts. We examine errors involving biological inconsistency, contextual inaccuracy, and agronomic implausibility, evaluating the outputs under domain-informed criteria across multiple imaging modalities. Our analysis identifies recurring hallucination patterns within both interpretive and generative tasks. In image interpretation, LLMs (e.g., Gemma, LLAVA, Qwen, and MiniCPM) achieved modest zero-shot accuracy (63 to 75 percent), whereas few-shot prompting improved performance up to 86.8 percent, exhibiting false detections and missed infections, indicating residual hallucination effects. In text-to-image tasks, advanced models such as GPT-5 and Gemini 2.5 Flash generate up to 91 percent biologically inconsistent scenes under relaxed prompt constraints, revealing fundamental weaknesses in current LLMs. This systematic assessment of visual reasoning and generation offers critical insights toward enhancing the reliability and trustworthiness of LLM-based agricultural imaging platforms.

Large language models (LLMs) are prone to hallucinations, i.e., statements unsupported by the input or training data, hindering reliable deployment. In parallel, numerous uncertainty estimation (UE) methods have been proposed to quantify model confidence and are often implicitly treated as proxies for model failure. However, the relationship between uncertainty and hallucinations remains insufficiently characterized. We present a systematic empirical study of the association between uncertainty estimators and hallucinations in LLMs. Rather than assuming this association, we evaluate directly when and to what extent it holds. We consider a diverse set of uncertainty estimators, including information-theoretic, sampling-based, and reflexive estimators, and examine their behavior across hallucination settings. Our experiments cover both intrinsic hallucinations (violations of input faithfulness) and extrinsic hallucinations (unsupported claims relative to training data), using four complementary benchmarks, including RAGTruth and HalluLens. We find that the association is highly variable and often weak, depending on the hallucination type and the LLM under evaluation. These results challenge the use of uncertainty as a direct signal of hallucination and clarify when it provides actionable information.

LLMs deployed in high-stakes domains face fundamental reliability challenges: hallucinations, inconsistencies, and privacy vulnerabilities introduce unacceptable risks where errors carry legal, financial, or safety consequences. This paper presents a hybrid verification architecture combining formal symbolic methods with neural semantic analysis to provide complementary guarantees for LLM-generated content. This architecture employs logical reasoning for input verification, leveraging completeness properties to provide decidable guarantees on structured requirements. For output validation, embedding-based semantic similarity detects contextual hallucinations where formal methods lack expressiveness. This separation is realized in a parallel, actor-based pipeline, addressing limitations of prompt-based self-verification approaches, which inherit the distributional biases that produce hallucinations. The proposed architecture and type-aware verification method are validated with HAIMEDA, a real-world medical device damage assessment reporting system developed through Action Design Research. Evaluation shows hallucination detection rates of over 83% for structured entities and 72% for semantic fabrications, with a 30% reduction in report creation time, demonstrating that neuro-symbolic architectures can provide principled safeguards for LLM deployment in data-sensitive domains.

Hallucination is a central limitation of large language models (LLMs), and substantial effort has been devoted to understanding and mitigating it. Towards this, Kalai and Vempala (STOC 2024) introduced a probabilistic framework formalizing calibration and hallucination, and showed that, with high probability, calibrated LLMs hallucinate roughly at the rate of the "missing mass", a measure of how incomplete the training data is relative to its source. This raises two fundamental questions: (i) what property of a calibrated LLM makes hallucinations unavoidable? and (ii) can hallucinations be avoided by giving up calibration? We answer these questions by introducing a simpler property we call innovation that measures the tendency of a model to produce outputs outside the training data. We show that innovation is implied by the condition for hallucination identified by Kalai and Vempala, and, further, that it is an almost characterization of hallucination: hallucination implies innovation, and conversely, innovation implies hallucination with high probability. We also provide lower bounds on the hallucination rate based on the "innovation rate", and by relating innovation rate back to missing mass, we obtain new hallucination rate lower bounds based on missing mass that extend the results of Kalai and Vempala.

In many reasoning tasks, large language models (LLMs) rely on structured external knowledge, such as graphs and tables, which is typically linearized into sequential token representations. However, even when sufficient knowledge is available, LLMs can still produce hallucinated outputs, and the underlying mechanisms behind such failures remain poorly understood. We investigate these mechanisms and find that hallucinations arise from systematic internal dynamics rather than random noise. First, attention disproportionately concentrates toward shortcut-like structural cues rather than distributing across the full context. Second, feed-forward representations fail to ground the provided knowledge, causing the model to revert to parametric memory. Moreover, our results indicate that hallucination is consistently associated with failures in semantic grounding within feed-forward layers, while attention allocation exhibits greater task-dependent variability. Finally, we show that these mechanistic patterns generalize beyond single-hop graphs to multi-hop and tabular settings, enabling effective hallucination detection across structured knowledge formats.

Large Vision-Language Models (LVLMs) have advanced multimodal understanding, yet their reliability is limited by hallucination, where generated content conflicts with visual facts. Existing mitigation methods either rely on costly external interventions, such as instruction tuning and retrieval, or use internal mechanisms that remain limited by flawed attention weights and entangled hidden representations. We propose Adversarial Orthogonal Disentanglement (AOD), a latent geometric framework for mitigating LVLM hallucinations. AOD learns a hallucination-related direction through a minimax objective: a classifier concentrates hallucination signals into the projected component, while an adversary removes them from the orthogonal residual space via a Gradient Reversal Layer. The learned direction enables a training-free dual-forward-pass contrastive decoding strategy that suppresses hallucinations while preserving general capabilities. Experiments on three LVLMs across four hallucination and four utility benchmarks show that AOD consistently outperforms strong baselines. It improves POPE accuracy by over 6% on average, boosts AMBER by 6%, and maintains strong performance on utility tasks such as MMMU. Further analysis shows robust transfer across datasets, suggesting that AOD captures general hallucination-related biases rather than dataset-specific artifacts. Our source code and datasets are available at https://github.com/Hunter-Wrynn/AOD.

Large Language Models (LLMs) are optimized to produce distributionally plausible continuations rather than to explicitly verify whether generated propositions are entailed by source documents. This inductive bias enables generalization, but it does not encode whether responses are grounded with respect to a reference. These issues limit the use of LLMs in domains where strict factual correctness is crucial, such as clinical decision support. Existing hallucination detection approaches improve factuality through retrieval augmentation, self-consistency, or claim verification, but generally do not learn directly over alignment topology. To leverage alignment topology as an inductive bias, we construct aligned bipartite graphs between reference information and LLM outputs and train a graph neural network (GNN) to model alignment structure using message passing. The method achieves state-of-the-art results on four diverse hallucination and question-answering datasets, outperforming all compared methods, including foundational LLMs such as GPT-4o.

Hallucination is often viewed as a direct consequence of missing knowledge: a model answers incorrectly when the correct answer is absent from its generation-time distribution, and correctly when it is present. We test this assumption by introducing a semantic notion of answer availability that aggregates token-level variants expressing the same answer concept, and asks whether the correct concept is already available at the moment the model commits to an answer. Across Qwen and Llama models from 0.8B to 72B in both Instruct and Base variants, 16-47% of Instruct hallucinations occur with substantial probability mass already on the correct concept, and the rate rises monotonically with scale. Comparing such failures against correct generations with matched semantic support, the distinguishing factor is not whether the correct concept is represented, but how its probability is distributed: correct generations concentrate mass on a single surface form, hallucinations disperse it across alternatives. The same sharpening asymmetry extends across multi-token generation and is detectable in pre-generation hidden states. Together, these results identify a single mechanism: instruction tuning sharpens answer commitment with scale, making helpfulness and confident hallucination two consequences of the same underlying disposition.

Large vision-language models (LVLMs) often hallucinate content that is fluent yet unsupported by the image, limiting their reliability in real-world deployment. We show that a key failure mode arises from route competition: even when visual tokens receive attention, the final token decision can be dominated by the textual pathway, causing the decoder to follow linguistic priors over visual evidence. To mitigate this, we propose a training-free, decision-aligned intervention that decomposes each attention head into a visual route and a text route, and estimates their token-level effects using an efficient one-forward/one-gradient approximation. These estimates reveal route conflict within heads and identify prior-dominant ones, enabling selective suppression of only the text route while keeping the visual route intact. Across five benchmarks spanning discriminative and generative settings, our method consistently reduces hallucination-related errors across models with limited impact on overall multimodal performance, while incurring a modest inference-time overhead.

Large Vision-Language Models (LVLMs) have shown remarkable performance on a wide range of vision-language tasks. Despite this progress, they are still prone to hallucination, generating responses that are inconsistent with visual content. In this work, we find that LVLMs tend to hallucinate when they pay insufficient attention to the correct visual evidence and gradually forget it during the generation process. We empirically find that although LVLMs overall attend insufficiently to visual evidence, they exhibit sensitivity to the correct visual evidence in specific layers, with notable inter-layer discrepancy. Motivated by this observation, we propose a novel hallucination mitigation method that enhances visual evidence based on Inter-Layer Visual Attention Discrepancy (ILVAD). Specifically, we obtain the attention weights from early generated tokens to visual tokens across layers and identify the tokens that are repeatedly activated as visual evidence, forming a saliency map. We then enhance attention to visual evidence during generation through the saliency map to reduce visual forgetting. In addition, we leverage the saliency map to obtain attention scores of generated text to visual evidence, in order to select and emphasize text tokens that are strongly grounded in visual evidence. Our method is training-free and plug-and-play. Multiple benchmark evaluations conducted on five recently released models show that our method can consistently mitigate hallucinations in different LVLMs over various architectures. Code is available at https://github.com/ytx-ML/ILVAD.

Large vision-language models (LVLMs) often hallucinate when language priors dominate weak or ambiguous visual evidence. Existing contrastive decoding methods mitigate this problem by comparing predictions from the original image with those from externally perturbed visual inputs, but such references can introduce off-manifold artifacts and require costly extra forward passes. We propose SIRA, a training-free internal contrastive decoding framework that constructs a counterfactual reference inside the same LVLM by exploiting the staged information flow of multimodal transformers. Instead of removing visual information from the input, SIRA first lets image and text tokens interact through a shared prefix, forming an aligned multimodal state that preserves prompt interpretation, decoding history, positional structure, and early visual grounding. It then forks a counterfactual branch in later transformer layers, where attention to image-token positions is masked. This branch retains the shared multimodal context but lacks continued access to fine-grained visual evidence, yielding a language-prior-dominated internal reference for token-level contrast. During decoding, SIRA suppresses tokens that remain strong without late visual access and favors predictions whose advantage depends on the full visual pathway. Experiments on POPE, CHAIR, and AMBER with Qwen2.5-VL and LLaVA-v1.5 show that SIRA consistently reduces hallucinations while preserving descriptive coverage and incurring lower overhead than two-pass contrastive decoding. SIRA requires no training, external verifier, or perturbed input, and applies to open-weight LVLMs with white-box inference access.

Hallucination remains a fundamental challenge in vision-language models (VLMs), where autoregressive generation may produce linguistically plausible yet physically inconsistent or visually ungrounded responses due to likelihood maximization under joint probabilistic modeling. We propose a stage-wise preference optimization framework for hallucination reduction through targeted multimodal data construction. Rather than directly optimizing on generic instruction-following data, our approach progressively constructs hallucination-focused preference pairs near known failure boundaries. The framework emphasizes ambiguous spatial orientation, object relationships, OCR uncertainty, and adversarial false-premise training. Hallucinated negatives are generated through minimally perturbed yet visually inconsistent alternatives, enabling Direct Preference Optimization (DPO) to better separate grounded reasoning from plausible hallucination. Experiments on open-source benchmarks and real-world multimodal evaluation scenarios demonstrate improved grounding consistency, reduced hallucination, and more informative grounded responses. Cross-model qualitative evaluation further shows that the proposed multimodal LLM DPO framework produces more visually grounded responses than several frontier proprietary VLMs, such as in ambiguous spatial reasoning and adversarial false-premise settings. The results suggest that hallucination may arise not only from limited model capacity, but also from inherent tendencies of autoregressive probabilistic generation to favor linguistically plausible continuations under weak visual grounding. Future work may explore physical consistency modeling, uncertainty-aware multimodal reasoning, and architectural alternatives beyond standard autoregressive decoding.

Large language models (LLMs) achieve strong performance across many tasks but remain vulnerable to hallucinations, making it important to systematically evaluate their reliability under realistic adversarial inputs. We formulate hallucination elicitation as a constrained optimization problem, where the goal is to find semantically coherent adversarial prompts that are equivalent to benign user prompts. Existing attack methods remain limited: discrete prompt-based attacks preserve semantic equivalence and coherence but search only over a limited set of prompt variations, while continuous latent-space attacks explore a richer space but often decode into prompts that are no longer valid rephrasings. To address these limitations, we propose REALISTA, a realistic latent-space attack framework. REALISTA constructs an input-dependent dictionary of valid editing directions, each corresponding to a semantically equivalent and coherent rephrasing, and optimizes continuous combinations of these directions in latent space. This design combines the optimization flexibility of continuous attacks with the semantic realism of discrete rephrasing-based attacks. Experiments demonstrate that REALISTA achieves superior or comparable performance to state-of-the-art realistic attacks on open-source LLMs and, crucially, succeeds in attacking large reasoning models under free-form response settings, where prior realistic attacks fail. Code is available at https://github.com/Buyun-Liang/REALISTA.

Multimodal large language models (MLLMs) have become a key interface for visual reasoning and grounded question answering, yet they remain vulnerable to visual hallucinations, where generated responses contradict image content or mention nonexistent objects. A central challenge is that hallucination is not always caused by a simple lack of visual attention: the model may still assign substantial attention mass to image tokens while internally drifting toward an incorrect answer. In this paper, we show that the high-frequency structure of visual attention, measured by layer-wise Laplacian energy, reveals both the layer where hallucinated preferences emerge and the layer where the ground-truth answer transiently recovers. Building on this finding, we propose LaSCD (Laplacian-Spectral Contrastive Decoding), a training-free decoding strategy that selects informative layers via Laplacian energy and remaps next-token logits in closed form. Experiments on hallucination and general multimodal benchmarks show that LaSCD consistently reduces hallucination while preserving general capabilities, highlighting its potential as a faithful decoding paradigm. The code is available at https://github.com/macovaseas/LaSCD.

Hallucination, broadly referring to unfaithful, fabricated, or inconsistent content generated by LLMs, has wide-ranging implications. Therefore, a large body of effort has been devoted to detecting LLM hallucinations, as well as designing benchmark datasets for evaluating these detectors. In this work, we first establish a desiderata of properties for hallucination detection benchmarks (HDBs) to exhibit for effective evaluation. A critical look at existing HDBs through the lens of our desiderata reveals that none of them exhibits all the properties. We identify two largest gaps: (1) RAG-based grounded benchmarks with long context are severely lacking (partly because length impedes human annotation); and (2) Existing benchmarks do not make available realistic label noise for stress-testing detectors although real-world use-cases often grapple with label noise due to human or automated/weak annotation. To close these gaps, we build and open-source a new RAG-based HDB called T RIVIA+ that underwent a rigorous human annotation process. Notably, our benchmark exhibits all desirable properties including (1) T RIVIA+ contains samples with the longest context in the literature; and (2) we design and share four sets of noisy labels with different, both sample-dependent and sampleindependent, noise schemes. Finally, we perform experiments on RAG-based HDBs, including our T RIVIA+, using popular SOTA detectors that reveal new insights: (i) ample room remains for current detectors to reach the performance ceiling on RAG-based HDBs, (ii) the basic LLM-as-a-Judge baseline performs competitively, and (iii) label noise hinders detection performance. We expect that our findings, along with our proposed benchmark 1 , will motivate and foster needed research on hallucination detection for RAG-based tasks.

We study language generation in the limit under a global preference ordering on strings, as introduced by Kleinberg and Wei. As is done in previous work, we aim for breadth, but impose an additional requirement of timeliness: higher-ranked strings should be generated earlier. A string is then only credited if it is generated before a deadline, where its deadline is defined by a function that maps a string's rank in the target language to the time by which it must be produced. This is in keeping with a central consideration in machine learning, where inductive bias favors simpler'' or more plausible'' outputs, all else being equal. We show that timely generation is impossible in a strong sense for eventually consistent generators -- the protagonists of most prior related work. Under what is perhaps the mildest natural relaxation of consistency, a hallucination rate that vanishes over time, we show that we can circumvent our impossibility result. In particular, we can achieve optimal density with respect to any superlinear deadline function. We also show this is tight by ruling out timely generation with linear deadlines and vanishing hallucination rate.

During MLLM decoding, attention often abnormally concentrates on irrelevant image tokens. While existing research dismisses this as invalid noise and forcibly redirects attention to compel focusing on key image information, we argue these tokens are critical carriers of visual and narrative logic, and such coercive corrections exacerbate visual-language imbalance. Adopting a "decoding-as-game" perspective, we reveal that hallucinations stem from an equilibrium imbalance between linguistic priors and visual information. We propose Adversarial Counter-Commonsense Equilibrium (ACE), a training-free framework that perturbs visual context via counter-commonsense patches. Leveraging the fact that authentic visual features remain stable under perturbation while hallucinations fluctuate, ACE implements a dynamic game decoding strategy. This approach precisely suppresses perturbation-sensitive priors while compensating for stable visual signals to restore balance. Extensive experiments demonstrate that ACE, as a plug-and-play strategy, enhances model trustworthiness with negligible inference overhead.

Long-form video understanding remains challenging for Video Large Language Models (VideoLLMs), as the dense frame sampling introduces massive visual tokens while sparse sampling risks missing critical temporal evidence and leading to LLM hallucination. Existing training-free token reduction methods either treat videos equally as static images or rely on segment-level merging heuristics, which weaken fine-grained spatiotemporal modeling and introduce additional overhead. In this paper, we propose EchoPrune, a lightweight and training-free token pruning method that improves temporal resolution under a fixed LLM-side visual token budget. Our core idea is to interpret redundant video tokens as temporal echoes: if a token is well reconstructed from the previous frame, it is merely a temporally redundant echo; otherwise, it may capture new events, motion, or query-relevant visual evidence. Based on this insight, EchoPrune scores visual tokens by (i) query-guided crossmodal relevance and (ii) temporal reconstruction error, measured by correspondence matching and echo matching across consecutive frames. The selected tokens preserve task-relevant cues and temporal novelty while suppressing predictable redundancy, allowing VideoLLMs to observe more frames without increasing the decoding budget. Extensive experiments on LLaVA-OV, Qwen2.5VL, and Qwen3VL across six video understanding benchmarks show that EchoPrune enables VideoLLMs to process up to 20x frames under the same token budget, yielding improved performance (+8.6%) and inference speedup (5.6x for prefilling) on Qwen2.5VL-7B.

Large language models (LLMs) are known to generate plausible but false information across a wide range of contexts, yet the real-world magnitude and consequences of this hallucination problem remain poorly understood. Here we leverage a uniquely verifiable object - scientific citations - to audit 111 million references across 2.5 million papers in arXiv, bioRxiv, SSRN, and PubMed Central. We find a sharp rise in non-existent references following widespread LLM adoption, with a conservative estimate of 146,932 hallucinated citations in 2025 alone. These errors are diffusely embedded across many papers but especially pronounced in fields with rapid AI uptake, in manuscripts with linguistic signatures of AI-assisted writing, and among small and early-career author teams. At the same time, hallucinated references disproportionately assign credit to already prominent and male scholars, suggesting that LLM-generated errors may reinforce existing inequities in scientific recognition. Preprint moderation and journal publication processes capture only a fraction of these errors, suggesting that the spread of hallucinated content has outpaced existing safeguards. Together, these findings demonstrate that LLM hallucinations are infiltrating knowledge production at scale, threatening both the reliability and equity of future scientific discovery as human and AI systems draw on the existing literature.

Real-world audio-visual understanding requires chaining evidence that is sparse, temporally dispersed, and split across the visual and auditory streams, whereas existing benchmarks largely fail to evaluate this capability. They restrict videos to short clips, isolate modalities, or reduce questions to one-hop perception. We introduce TraceAV-Bench, the first benchmark to jointly evaluate multi-hop reasoning over long audio-visual trajectories and multimodal hallucination robustness. TraceAV-Bench comprises 2,200 rigorously validated multiple-choice questions over 578 long videos, totaling 339.5 hours, spanning 4 evaluation dimensions and 15 sub-tasks. Each question is grounded in an explicit reasoning chain that averages 3.68 hops across a 15.1-minute temporal span. The dataset is built by a three-step semi-automated pipeline followed by a strict quality assurance process. Evaluation of multiple representative OmniLLMs on TraceAV-Bench reveals that the benchmark poses a persistent challenge across all models, with the strongest closed-source model (Gemini 3.1 Pro) reaching only 68.29% on general tasks, and the best open-source model (Ming-Flash-Omni-2.0) reaching 51.70%, leaving substantial headroom. Moreover, we find that robustness to multimodal hallucination is largely decoupled from general multimodal reasoning performance. We anticipate that TraceAV-Bench will stimulate further research toward OmniLLMs that can reason coherently and faithfully over long-form audio-visual content.

Vision-Language Models (VLMs) increasingly power high-stakes applications, from medical imaging to autonomous systems, yet they routinely hallucinate, confidently describing content not present in the input. We investigate the root causes of these failure modes with a mechanistic analysis focusing on the decoder-based VLMs. We trace these failure modes to a geometric over-alignment: to bridge the modality gap required by attention mechanisms, decoder-based VLMs over-align visual embeddings with the text manifold, injecting a statistical linguistic bias that systematically overshadows fine-grained visual evidence. While prior work either aggressively closes this gap or suppresses hallucinations through expensive black-box decoding strategies, none addresses the underlying geometric cause. We provide the first quantitative characterization of this over-alignment, demonstrating that linguistic bias concentrates in the top principal components of a universal, dataset-agnostic text subspace. Building on this insight, we propose two complementary remedies: a training-free inference strategy and a bias-aware fine-tuning paradigm, both of which explicitly project out this subspace from visual representations. Our methods significantly reduce hallucinations across POPE, CHAIR, and AMBER benchmarks, and improve CLAIR scores on long-form captioning tasks, with the training-free variant adding no computational overhead over the base model.

One of the most critical challenges in Large Language Models is their tendency to hallucinate, i.e., produce factually incorrect responses. Existing approaches show promising results in terms of hallucination correction, but still suffer from a main limitation: they apply corrections indiscriminately to every token, corrupting also the originally correct generations. To overcome this drawback, we propose PCNET, a Probabilistic Circuit trained as a tractable density estimator over the LLM residual stream. The method detects hallucinations as geometric anomalies on the factual manifold, which is done via exact Negative Log-Likelihood computation, hence without the need for sampling, external verifiers, or weight modifications, as in existing techniques. To demonstrate its effectiveness, we exploit PCNET as a dynamic gate that distinguishes hallucinated from factual hidden states at each decoding step. This triggers our second main contribution, PC-LDCD (Probabilistic Circuit Latent Density Contrastive Decoding), only when the latent geometry deviates from factual regions, while leaving correct generations untouched. Across four LLMs, ranging from 1B to 8B models, and four benchmarks covering conversational reasoning, knowledge-intensive QA, reading comprehension, and truthfulness, PCNET achieves near-perfect hallucination detection across CoQA, SQuAD v2.0, and TriviaQA, with AUROC reaching up to 99%. Moreover, PC-LDCD obtains the highest True+Info, MC2, and MC3 scores on TruthfulQA in three out of four models, in comparison with state-of-the-art baselines, while reducing the mean corruption rate to 53.7% and achieving a preservation rate of 79.3%. Our proposed method is publicly available on GitHub.

Language models draw on two knowledge sources: facts baked into weights (parametric memory, PM) and information in context (working memory, WM). We study two mechanistically distinct failure modes--conflict, when PM and WM disagree and interfere; and hallucination, when the queried fact was never learned. Both produce confident output regardless, making output-based monitoring blind by design. We show both failures share a unified geometric account. In the hidden-state space of autoregressive generation, learned facts form attractor basins. Conflict is basin competition: WM disrupts convergence to the correct basin without raising output entropy. Hallucination is basin absence: the hidden state drifts freely when no memorized basin exists. The frozen LM head, designed for next-token prediction, cannot distinguish these cases and fires confidently either way. We verify this account in a controlled synthetic task-entity identifiers mapped to unique codes with PM installed via LoRA adapters--where ground truth is exact and component roles can be causally isolated through targeted adapter placement. Geometric margin--the hidden state's distance to the nearest memorized basin--reads this geometry directly and separates correct recall from hallucination far more cleanly than output entropy, with zero false refusals where entropy-based detection cannot avoid rejecting the vast majority of correct outputs. The separation holds on natural-language factual queries from the pretrained model with no adaptation, confirming attractor geometry is structural rather than a fine-tuning artifact. The fraction of confident hallucinations follows a scaling law $C = \exp(-c/\barΔ)$, growing with scale even as overall error rates fall. Hidden states reliably encode epistemic state; the frozen output head systematically erases it--and this erasure worsens with scale.

Large Language Models (LLMs) frequently generate plausible but non-factual content, a phenomenon known as hallucination. While existing detection methods typically rely on computationally expensive sampling-based consistency checks or external knowledge retrieval, we propose a new method that treats the LLM as a black-box dynamical system. By projecting LLM responses into a high-dimensional manifold via an embedding model, we characterize the resulting vector sequences as observable realizations of the model's latent state-space dynamics. Leveraging Koopman operator theory, we fit the transition operators for both factual and hallucinated regimes and define a differential residual score based on their respective prediction errors. To accommodate varying user requirements and domain-specific sensitivities, we introduce a preference-aware calibration mechanism that optimizes the classification threshold based on a small set of demonstrations. This approach enables low-cost hallucination detection in a single-sample pass, avoiding the need for secondary sampling or external grounding. Extensive testing across three data benchmarks demonstrates that our method achieves state-of-the-art performance with reduced resource overhead.

Vision-language models (VLMs) achieve strong multimodal performance but remain prone to relation hallucination, which requires accurate reasoning over inter-object interactions. We study the impact of visual perturbations, specifically rotation and noise, and show that even mild distortions significantly degrade relational reasoning across models and datasets. We further evaluate prompt-based augmentation and preprocessing strategies (orientation correction and denoising), finding that while they offer partial improvements, they do not fully resolve hallucinations. Our results reveal a gap between perceptual robustness and relational understanding, highlighting the need for more robust, geometry-aware VLMs.

Large Language Models (LLMs) are prone to factual hallucinations, risking their reliability in real-world applications. Existing hallucination detectors mainly extract micro-level intrinsic patterns for uncertainty quantification or elicit macro-level self-judgments through verbalized prompts. However, these methods address only a single facet of the hallucination, focusing either on implicit neural uncertainty or explicit symbolic reasoning, thereby treating these inherently coupled behaviors in isolation and failing to exploit their interdependence for a holistic view. In this paper, we propose LaaB (Logical Consistency-as-a-Bridge), a framework that bridges neural features and symbolic judgments for hallucination detection. LaaB introduces a "meta-judgment" process to map symbolic labels back into the feature space. By leveraging the inherent logical bridge where response and meta-judgment labels are either the same or opposite based on the self-judgment's semantics, LaaB aligns and integrates dual-view signals via mutual learning and enhances the hallucination detection. Extensive experiments on 4 public datasets, across 4 LLMs, against 8 baselines demonstrate the superiority of LaaB.

With the rapid advancement of large language models (LLMs), classic graph learning tasks have greatly benefited from LLMs, including improved encoding of textual features, more efficient construction of graphs from text, and enhanced reasoning over knowledge graphs. In this paper, we ask a complementary question: How can graphs help LLMs? We address this question from three perspectives: 1) graphs provide an up-to-date knowledge source that helps reduce LLM hallucinations, 2) graph-based prompting techniques-such as Chain-of-Thought (CoT), Tree-of-Thought (ToT), and Graph-of-Thought (GoT)-enhance LLM reasoning capabilities, and 3) integrating graphs into LLMs improves their understanding of structured data, expanding their applicability to domains such as e-commerce, code, and relational databases (RDBs). We further outlook some future directions including designing sparse LLM architectures based on graphs and brain-inspired memory systems.

Multimodal large language models (MLLMs) have revolutionized the landscape of AI, demonstrating impressive capabilities in tackling complex vision and audio-language tasks. However, a critical challenge remains: these models often suffer from hallucinations, generating outputs that diverge from the provided perceptual inputs. This tendency stems from an inherent imbalance in modality utilization during inference, where the dominance of textual tokens undermines the potential of perceptual inputs. As a result, the model frequently resorts to textual language priors at the expense of grounded evidence. To tackle this issue, we propose Learning Inference-time Modality Enhancement (LIME), a training-free framework designed to bolster multimodal grounding by explicitly enhancing modality usage during decoding. LIME leverages Layer-wise Relevance Propagation (LRP) to quantify token-level contributions and defines a relevance-based objective that promotes increased reliance on perceptual inputs. This objective is enforced through inference-time updates to the model's key-value representations, without modifying model parameters or requiring additional training data. We evaluate LIME across multiple multimodal benchmarks in both vision and audio domains, demonstrating consistent reductions in hallucinations and enhanced grounding while preserving generation quality. Further analysis shows that LIME increases modality contribution and produces more localized and semantically aligned relevance patterns.

Hallucinations remain an unsolved problem for LLMs, and package hallucinations are a particularly dangerous instance of this phenomenon. Package hallucinations occur during code generation when a model fabricates non-existent software packages, recommending imports and installation commands for fictional libraries. This creates a critical supply-chain vulnerability; an attacker can proactively register such packages on public registries with malicious payloads that are subsequently installed and executed by developers or autonomous agents. These hallucinations enable a class of package confusion attack known as slopsquatting. To address this issue, we present Adaptive Unlearning (AU), a post-deployment framework that surgically suppresses package hallucinations while preserving general model utility. AU introduces a hybrid token-level objective that simultaneously reinforces valid outputs and suppresses hallucinated ones. Combined with an adaptive discovery loop that continuously surfaces new hallucination-inducing contexts without human supervision, AU enables generalization to unseen prompts and hallucinations. We demonstrate that AU reduces package hallucination rates by 88%, while maintaining performance on standard coding benchmarks. Our analysis shows that distributional changes are concentrated on package-related generations, leaving general coding behavior largely unaffected and confirming that AU's effect is isolated to the targeted distribution. AU relies entirely on model-generated data and requires no human annotation, representing a post-deployment hallucination mitigation framework.

Large Vision-Language Models (LVLMs) often suffer from hallucinations, generating descriptions that include visual details absent from the input image. Recent preference alignment methods typically rely on supervision distilled from stronger models such as GPT. However, this offline paradigm introduces a Supervision-Perception Mismatch: the student model is forced to align with fine-grained details beyond its perceptual capacity, learning to guess rather than to see. To obtain reliable self-supervision for online learning, we identify a Generative-Discriminative Gap within LVLMs, where models exhibit higher accuracy on discriminative verification than open-ended generation. Leveraging this capability, we propose \textbf{O}nline \textbf{S}elf-\textbf{CA}lib\textbf{R}ation (OSCAR), a framework that integrates Monte Carlo Tree Search with a Dual-Granularity Reward Mechanism to construct preference data and iteratively refines the model via Direct Preference Optimization. Extensive experiments demonstrate that OSCAR achieves state-of-the-art performance on hallucination benchmarks while improving general multimodal capabilities.

Large language models (LLMs) acquire most of their factual knowledge during the pre-training stage, through next token prediction. Subsequent stages of post-training often introduce new facts outwith the parametric knowledge, giving rise to hallucinations. While it has been demonstrated that supervised fine-tuning (SFT) on new knowledge may exacerbate the problem, the underlying mechanisms are still poorly understood. We conduct a controlled fine-tuning experiment, focusing on closed-book QA, and find latent directions that causally contribute to hallucinations. Specifically, we fine-tune Llama 3.1 8B, Gemma 2 9B and Mistral 7B v03 on seven distinct single QA datasets, controlling for the percentage of new knowledge and number of training epochs. By measuring performance on the test set, we validate that incrementally introducing new knowledge increases hallucinations, with the effect being more pronounced with prolonged training. We leverage pre-trained sparse autoencoders (SAEs) to analyze residual stream activations across various checkpoints for each model and propose Monotonic Relationship Feature Identification (MoRFI) for capturing causally relevant latents. MoRFI filters SAE features that respond monotonically to controlled fine-tuning data mixtures of a target property. Our findings show that exposure to unknown facts disrupts the model's ability to retrieve stored knowledge along a set of directions in the residual stream. Our pipeline reliably discovers them across distinct models, recovering knowledge through single-latent interventions.

Large language models hallucinate--producing fluent, confident, factually wrong outputs--with a consistency that persists across generations and scales. Existing taxonomies classify hallucination by output type, distinguishing intrinsic from extrinsic failures and faithfulness from factuality divergence. These frameworks are descriptively rigorous but do not identify which internal mechanism produced a given instance. This paper analyses hallucination as a structural consequence of three architectural decisions that together form a compound failure system. Self-attention's co-occurrence learning substitutes statistical proximity for semantic meaning and produces entity confusion, fact misattribution, and semantic drift. The maximum likelihood estimation training objective optimises next-token probability without factual constraint, rewarding statistically plausible outputs regardless of their truth value. Autoregressive decoding's permanent left-to-right commitment under exposure bias ensures that a single wrong token cascades forward through the entire output sequence without revision. Dataset pathologies--long-tail deficiencies, training bias, and synthetic pollution--amplify these vulnerabilities but do not independently cause them. We make three contributions. First, we map each mechanism to a specific output category in the Alansari and Luqman taxonomy, locating intrinsic hallucination in self-attention, extrinsic hallucination in MLE, and logical inconsistency in autoregressive decoding. Second, we show that each commonly cited dataset pathology exploits one of these mechanisms rather than originating hallucination independently. Third, we identify the diagnostic limitation of output-type-only classification and contrast it with inference-layer mitigation approaches.

Large Vision-Language Models (VLMs) have achieved remarkable multimodal performance yet remain prone to factual hallucinations, particularly in long-tail or specialized domains. Moreover, current models exhibit a weak capacity to refuse queries that exceed their parametric knowledge. In this paper, we propose a systematic framework to enhance the refusal capability of VLMs when facing such unknown questions. We first curate a model-specific "Visual-Idk" (Visual-I don't know) dataset, leveraging multi-sample consistency probing to distinguish between known and unknown facts. We then align the model using supervised fine-tuning followed by preference-aware optimization (e.g., DPO, ORPO) to effectively delineate its knowledge boundaries. Results on the Visual-Idk dataset show our method improves the Truthful Rate from 57.9% to 67.3%. Additionally, internal probing also demonstrates that the model genuinely recognizes its boundaries instead of just memorizing refusal patterns. Our framework further generalizes to out-of-distribution medical and perceptual domains, providing a robust path toward more trustworthy and prudent visual assistants.

Large Vision-Language Models (LVLMs) have achieved remarkable progress in visual-textual understanding, yet their reliability is critically undermined by hallucinations, i.e., the generation of factually incorrect or inconsistent responses. While recent studies using steering vectors demonstrated promise in reducing hallucinations, a notable challenge remains: they inadvertently amplify the severity of residual hallucinations. We attribute this to their exclusive focus on the decoding stage, where errors accumulate autoregressively and progressively worsen subsequent hallucinatory outputs. To address this, we propose Prefill-Time Intervention (PTI), a novel steering paradigm that intervenes only once during the prefill stage, enhancing the initial Key-Value (KV) cache before error accumulation occurs. Specifically, PTI is modality-aware, deriving distinct directions for visual and textual representations. This intervention is decoupled to steer keys toward visually-grounded objects and values to filter background noise, correcting hallucination-prone representations at their source. Extensive experiments demonstrate PTI's significant performance in mitigating hallucinations and its generalizability across diverse decoding strategies, LVLMs, and benchmarks. Moreover, PTI is orthogonal to existing decoding-stage methods, enabling plug-and-play integration and further boosting performance. Code is available at: https://github.com/huaiyi66/PTI.

Large Vision-Language Models (LVLMs) frequently suffer from hallucinations. Existing preference learning-based approaches largely rely on proprietary models to construct preference datasets. We identify that this reliance introduces a distributional mismatch between the proprietary and target models that hinders efficient alignment. To address this, we propose Alignment via VErified Self-correction DPO (AVES-DPO), a framework that aligns LVLMs using in-distribution data derived from the model's intrinsic knowledge. Our approach employs a consensus-based verification mechanism to diagnose diverse hallucinations and guides the model to self-correct, thereby generating preference pairs strictly compatible with its internal distribution. Extensive experiments demonstrate that AVES-DPO surpasses existing baselines in hallucination mitigation while requiring only 5.2k samples.

Large language models (LLMs) often produce content that contradicts or overlooks information provided in the input context, a phenomenon known as faithfulness hallucination. In this paper, we propose Context-Fidelity Boosting (CFB), a lightweight and general decoding-time framework that reduces such hallucinations by increasing the generation probability of source-supported tokens. Motivated by logit-shaping principles from watermarking techniques, CFB applies additive token-level logit adjustments based on a token's degree of support from the input context. Specifically, we develop three boosting strategies: static boosting, which applies a fixed bias to source-supported tokens; context-aware boosting, which scales this bias using the divergence between next-token distributions with and without context; and token-aware boosting, which further redistributes the adaptive bias according to local relevance estimated from source-position attention and source-scoped semantic similarity. CFB requires no retraining or architectural changes, making it compatible with a wide range of LLMs. Experiments on summarization and question answering tasks across multiple open-source LLMs show that CFB consistently improves faithfulness metrics with minimal generation overhead. Our implementation is fully open-sourced.

Despite impressive progress in capabilities of large vision-language models (LVLMs), these systems remain vulnerable to hallucinations, i.e., outputs that are not grounded in the visual input. Prior work has attributed hallucinations in LVLMs to factors such as limitations of the vision backbone or the dominance of the language component, yet the relative importance of these factors remains unclear. To resolve this ambiguity, We propose HalluScope, a benchmark to better understand the extent to which different factors induce hallucinations. Our analysis indicates that hallucinations largely stem from excessive reliance on textual priors and background knowledge, especially information introduced through textual instructions. To mitigate hallucinations induced by textual instruction priors, we propose HalluVL-DPO, a framework for fine-tuning off-the-shelf LVLMs towards more visually grounded responses. HalluVL-DPO leverages preference optimization using a curated training dataset that we construct, guiding the model to prefer grounded responses over hallucinated ones. We demonstrate that our optimized model effectively mitigates the targeted hallucination failure mode, while preserving or improving performance on other hallucination benchmarks and visual capability evaluations. To support reproducibility and further research, we will publicly release our evaluation benchmark, preference training dataset, and code at https://pegah-kh.github.io/projects/prompts-override-vision/ .

Large Vision-Language Models (LVLMs) exhibit powerful generative capabilities but frequently produce hallucinations that compromise output reliability. Fine-tuning on annotated data devoid of hallucinations offers the most direct solution, while its high computational cost motivates recent representation-based methods, which focus on mitigating hallucinatory components within hidden representations. Though efficient, we empirically observe that these methods degrade general generation capacity due to incomplete extraction of hallucination components and non-selective parameter updates. To address these limitations, we propose MPD, a dual-stage framework for mitigating hallucinations without performance degradation. Specifically, our MPD relies on two essential factors: (1) semantic-aware component disentanglement to extract pure hallucination components, and (2) interpretable parameter updates that selectively modify parameters most relevant to hallucination. Extensive experiments demonstrate that MPD achieves state-of-the-art performance, reducing hallucinations by 23.4% while maintaining 97.4% of general generative capability as evaluated on LLaVA-Bench and MME, with no additional computational cost.

This paper studies uncertainty quantification for large language models (LLMs) under black-box access, where only a small number of responses can be sampled for each query. In this setting, estimating the effective semantic alphabet size--that is, the number of distinct meanings expressed in the sampled responses--provides a useful proxy for downstream risk. However, frequency-based estimators tend to undercount rare semantic modes when the sample size is small, while graph-spectral quantities alone are not designed to estimate semantic occupancy accurately. To address this issue, we propose SHADE (Soft-Hybrid Alphabet Dynamic Estimator), a simple and interpretable estimator that combines Generalized Good-Turing coverage with a heat-kernel trace of the normalized Laplacian constructed from an entailment-weighted graph over sampled responses. The estimated coverage adaptively determines the fusion rule: under high coverage, SHADE uses a convex combination of the two signals, while under low coverage it applies a LogSumExp fusion to emphasize missing or weakly observed semantic modes. A finite-sample correction is then introduced to stabilize the resulting cardinality estimate before converting it into a coverage-adjusted semantic entropy score. Experiments on pooled semantic alphabet-size estimation against large-sample references and on QA incorrectness detection show that SHADE achieves the strongest improvements in the most sample-limited regime, while the performance gap narrows as the number of samples increases. These results suggest that hybrid semantic occupancy estimation is particularly beneficial when black-box uncertainty quantification must operate under tight sampling budgets.

LLMs frequently generate fictitious yet convincing citations, often expressing high confidence even when the underlying reference is wrong. We study this failure across 9 models and 108{,}000 generated references, and find that author names fail far more often than other fields across all models and settings. Citation style has no measurable effect, while reasoning-oriented distillation degrades recall. Probes trained on one field transfer at near-chance levels to the others, suggesting that hallucination signals do not generalize across fields. Building on this finding, we apply elastic-net regularization with stability selection to neuron-level CETT values of Qwen2.5-32B-Instruct and identify a sparse set of field-specific hallucination neurons (FH-neurons). Causal intervention further confirms their role: amplifying these neurons increases hallucination, while suppressing them improves performance across fields, with larger gains in some fields. These results suggest a lightweight approach to detecting and mitigating citation hallucination using internal model signals alone.

Large Vision-Language Models (LVLMs) still struggle with vision hallucination, where generated responses are inconsistent with the visual input. Existing methods either rely on large-scale annotated data for fine-tuning, which incurs massive computational overhead, or employ static post-hoc strategies that overlook the dynamic nature of hallucination emergence. To address these, we introduce a new self-rewarding framework, enabling dynamic hallucination mitigation at inference time without external supervision. On the empirical side, we reveal that visual hallucination exhibits phase-wise dynamic patterns, peaking at the onset of each semantic phase. Drawing on these insights, we propose \textbf{PSRD} (\textbf{Phase-wise \textbf{S}elf-\textbf{R}eward \textbf{D}ecoding) for online hallucination correction guided by phase-wise self-reward signals. To reduce the cost of repeated self-evaluation during decoding, we distill the hallucination guidance signal from LVLMs into a lightweight reward model. The reward model subsequently provides on-the-fly guidance for targeted intervention during the decoding process, enabling precise hallucination suppression. The proposed PSRD significantly reduces the hallucination rate of LLaVA-1.5-7B by 50.0% and consistently outperforms existing post-hoc methods across five hallucination evaluation benchmarks for four LVLMs. Further analysis confirms that PSRD effectively mitigates hallucination propagation and achieves a highly controllable trade-off between strong performance and inference efficiency.

This study investigates the phenomenon of hallucinations in domain-adapted Large Language Models (LLMs), focusing on the fine-tuning of the Llama-2 model with the Lamini dataset. Hallucinations, or the generation of nonsensical or unfaithful content by LLMs, pose a significant challenge, especially when these models are fine-tuned with domain-specific data. Our methodology involves a series of experiments testing memorization, recall, and reasoning capabilities of the fine-tuned LLM, comparing its performance on novel question-answer pairs and domain-specific information. We found that while the model shows proficiency in tasks similar to its training data, its capability to accurately reason about and recall new domain-specific information remains limited, leading to instances of hallucination. The model demonstrates a tendency to provide correct answers with extra information, suggesting an inclination toward over-generation. These results suggest important limitations of fine-tuning-only approaches for mitigating hallucinations when adapting LLMs to specialized domains and underscore the need for more robust methods in adapting LLMs to specialized domains. The study also provides insights into the varying performance of LLMs on different types of information, revealing a comparative weakness in handling domain-specific queries.

Recent advances in Vision-Language Models (VLMs) have substantially enhanced their ability across multimodal video understanding benchmarks spanning temporal, action, object, and spatial understanding. However, we identify a critical yet overlooked issue: when embedded on-screen text contradicts the visual scene, existing VLMs systematically hallucinate, prioritizing overlay textual semantics over the actual visual content. We define this phenomenon as Text Overlay-Induced Hallucination (TOIH). In this work, we propose VisualTextTrap, the first comprehensive benchmark, including large-scale human-validated samples with specifically designed evaluation metrics. In particular, we construct VisualTextTrap from widely-used public datasets using a scalable hybrid pipeline of VLMs assisted text generation and rigorous manual verification. The benchmark features 6,057 samples annotated across 88 fine-grained attributes within four dimensions, with hallucination intensity quantified on a five-level scale (L1--L5) that reflects the semantic contradiction between overlay text and visual reality. Moreover, we propose Visual Text Hallucination Mitigation Mixture-of-Experts (VTHM-MoE), a novel Vision-Text Disentanglement framework that employs a dual-encoder architecture. Concretely, four dimension-specialized expert modules spanning Temporal, Action, Object, and Spatial reasoning are first pre-trained to identify and leverage cross-modal discrepancies between textual semantics and actual video content. We develop an Adaptive Token Routing Strategy to enable dynamic expert allocation, conferring robust resistance to TOIH while preserving performance on uncontaminated videos. Extensive experiments conducted on our VisualTextTrap benchmark verify the effectiveness of VTHM-MoE, outperforming state-of-the-art counterparts with diverse video question answering tasks.

The accurate extraction of scientific measurements from literature is a critical yet challenging task in AI4Science, enabling large-scale analysis and integration of quantitative research findings. However, Large Language Models (LLMs) frequently exhibit severe hallucinations, which significantly undermine the reliability of automated scientific document understanding systems. To address this problem, we propose MeasHalu, a novel framework for mitigating scientific measurement hallucinations through enhanced reasoning and targeted optimization. We first present a fine-grained taxonomy of measurement-specific hallucinations, categorizing errors across quantities, units, modifiers, and relations. Our approach incorporates a two-stage reasoning-aware fine-tuning strategy using augmented scientific data and process-based supervision. Furthermore, we introduce a progressive reward curriculum designed to penalize specific hallucination types, significantly improving extraction faithfulness. Experimental results demonstrate that MeasHalu substantially reduces hallucination rates and improves overall accuracy on the MeasEval benchmark. This work provides a targeted solution to a key bottleneck in automated scientific knowledge extraction, facilitating more trustworthy and scalable machine-assisted scientific literature analysis.

As large language models (LLMs) evolve from conversational assistants into agents capable of handling complex tasks, they are increasingly deployed in high-risk domains. However, existing benchmarks largely rely on mixed queries and posterior evaluation, output-level scoring, which quantifies hallucination severity but offers limited insight into where and why hallucinations arise in the generation pipeline. We therefore reformulate hallucination evaluation as a diagnostic problem and propose PRISM, a controlled benchmark that disentangles hallucinations into four dimensions: knowledge missing, knowledge errors, reasoning errors, and instruction-following errors, grounded in three stages of generation (memory, instruction, and reasoning). PRISM contains 9,448 instances across 65 tasks and supports fine-grained, stage-aware diagnostic evaluation. Evaluating 24 mainstream open-source and proprietary LLMs, we uncover consistent trade-offs across instruction following, memory retrieval, and logical reasoning, showing that mitigation strategies often improve specific dimensions at the expense of others. We hope PRISM provides a framework for understanding the specific mechanisms behind LLMs hallucinations, ultimately accelerating the development of trustworthy large language models.

Retrieval-Augmented Generation (RAG) is widely used to augment the input to Large Language Models (LLMs) with external information, such as recent or domain-specific knowledge. Nonetheless, current models still produce closed-domain hallucinations and generate content that is unsupported by the retrieved context. Current detection approaches typically treat hallucination as a post-hoc problem, relying on black-box consistency checks or probes over frozen internal representations. In this work, we demonstrate that hallucination detection based on internal state representation can also serve as a direct training signal. We introduce RAGognize, a dataset of naturally occurring closed-domain hallucinations with token-level annotations, and RAGognizer, a hallucination-aware fine-tuning approach that integrates a lightweight detection head into an LLM, allowing for the joint optimization of language modeling and hallucination detection. This joint objective forces the model to improve the separability of its internal states regarding hallucinations while simultaneously learning to generate well-formed and meaningful responses. Across multiple benchmarks, RAGognizer achieves state-of-the-art token-level hallucination detection while substantially reducing hallucination rates during generation, without degrading language quality or relevance.

Large language models are prone to hallucinating factually incorrect statements. A key source of these errors is exposure to new factual information through supervised fine-tuning (SFT), which can increase hallucinations w.r.t.~knowledge acquired during pre-training. Since these errors arise as a by-product of knowledge degradation, we explore whether established continual learning tools can mitigate them. We propose a self-distillation-based SFT method that facilitates effective factual learning while minimizing hallucinations w.r.t.~pre-existing knowledge by regularizing output-distribution drift. We also show that when new knowledge acquisition is unnecessary, suppressing factual plasticity by freezing parameter groups preserves task performance while reducing hallucinations. Lastly, we investigate the mechanism, contrasting capacity limitations, behavior cloning, and localized interference. Our experiments show that a main driver is interference among overlapping semantic representations, which self-distillation mitigates and an associative-memory model explains: forgetting grows with the overlap between new and stored facts.

Large Language Models (LLMs) have demonstrated advanced capabilities but often suffer from factual inaccuracies (hallucinations) and systematic biases. These issues, sometimes amplified in specific architectures like Mixture-of-Experts (MoE) which motivate our work, pose risks for reliable deployment. To address these challenges, we propose the Council Mode, a multi-agent consensus framework. Our approach dispatches queries to multiple heterogeneous frontier LLMs in parallel and synthesizes their outputs using a dedicated consensus model. The pipeline consists of three phases: an intelligent triage for query complexity, parallel generation across diverse models, and a structured synthesis that identifies agreement, disagreement, and unique findings. In our evaluation, conducted under controlled no-web settings, the Council Mode achieved a 41.7% relative reduction in hallucination rates on a 1,200-sample HaluEval subset and a 7.5-point improvement on TruthfulQA compared to the top-performing individual model. On our curated MDR-500 multi-domain reasoning benchmark, the Council Mode achieved a Quality Score of 95.4%, representing a 9.2-point improvement over the best individual model. The framework also exhibited lower measured bias variance under our rubric-based evaluation protocol. We provide a cost-effectiveness analysis showing that the framework incurs a 4.2x token-cost overhead, making it most suitable for accuracy-prioritized applications where the cost of errors exceeds the added inference cost. These findings suggest that structured multi-agent consensus is a promising direction for enhancing the reliability and factual grounding of LLM-generated content.