Hallucination Rate

Hallucinations can undermine clinician trust in LLMs, making it important that evaluation methods capture clinically relevant errors. Rubric-based evaluation has become the leading approach for assessing LLMs in medicine, but it is unclear whether rubric scores reflect such errors. We first study this in a controlled setting using MedHallu, finding that more specific rubrics better distinguish correct from hallucinated responses. To test this systematically, we develop a taxonomy of medical hallucination types and a clinician-validated error-injection pipeline that creates matched correct and error-injected responses. Across HealthBench, HealthBench Professional, and LiveMedBench, our clinically relevant hallucinations are missed by rubrics, often leaving scores unchanged. We find that rubrics are most effective when explicitly checking facts, and are less effective for additional or unexpected errors they do not anticipate. A preliminary retrieval-based factuality check recovers some of the rubric-blind errors, suggesting a complementary approach. These findings reveal systematic blind spots in current medical evaluation of LLMs and suggest that rubric scores alone are insufficient to establish clinical reliability, potentially undermining clinician trust and confidence in clinical deployment.

As large language models are increasingly deployed as tool-augmented legal agents, they introduce agentic hallucinations where tool-call and reasoning errors cascade into fabricated holdings and miscited authority. However, existing legal benchmarks evaluate only single-turn QA with outcome-level metrics, while agentic hallucination benchmarks lack legal-specific diagnostic capability. Neither answers to what extent and how a legal agent hallucinates along its trajectory. To address these limitations, we introduce LexAgentHallu, a legal agentic hallucination benchmark designed to evaluate to what extent and how legal agents fail along multi-step trajectories. Built through a four-stage expert-in-the-loop pipeline, LexAgentHallu contains 3414 instances across 17 legal categories and 6 task types. Each instance is annotated under a dual-layer hallucination taxonomy of 7 high-level categories and 27 fine-grained subclasses, covering both substantive errors and agent-procedural failures. We further design fine-grained metrics that quantify to what extent and localize how each failure occurs along an agent's execution path. Our evaluation across 18 proprietary and open-source agents uncovers a Right-Answer-Wrong-Reason effect and reveals that hallucination subclasses cluster rather than scatter, forming distinct agentic framework, legal task, and category profiles. These findings, invisible to outcome-level evaluation, validate the diagnostic power of LexAgentHallu for evaluating agentic hallucination in law.

The growing scale of academic peer review has motivated the use of Large Language Models (LLMs) as review assistants, yet LLMs can generate fluent but unsupported claims that undermine review reliability. Existing hallucination benchmarks are not designed for peer review, where verification requires grounding claims in long, technical papers. We introduce HalluPeer, a benchmark for detecting hallucinations in scientific peer reviews, providing aligned triples of paper content, human-written reviews, and hallucination-injected reviews, annotated for detection, classification, and localization. Our pipeline induces a peer-review-specific hallucination taxonomy, identifies review contexts, and injects hallucinations with automated filtering. Experiments on 12K papers and 38K reviews show that existing detectors struggle to separate hallucinations from legitimate critique, while evaluation on authentic reviews demonstrates that HalluPeer-defined hallucination patterns occur in real peer reviews, highlighting the critical need for source-aware verification. Our project page can be found in https://github.com/Lin-TzuLing/HalluPeer.git

Recent inference-time hallucination mitigation methods for large vision-language models (LVLMs) report strong gains on hallucination benchmarks. However, it remains unclear whether lower hallucination scores reflect improved multimodal grounding or more conservative generation. We evaluate six mitigation methods across three LVLMs and four benchmarks, including hallucination-focused evaluation and the diverse capability benchmark MMStar. Our analysis reveals two consistent patterns. First, hallucination reduction is often coupled with reduced informativeness: methods that lower hallucination rates also reduce object recall, visual coverage, or response detailedness. Second, improvements on hallucination benchmarks do not reliably transfer to broader multimodal capabilities, with methods showing inconsistent or degraded performance on fine-grained perception and reasoning tasks. Our findings suggest that current evaluation protocols may overestimate progress by rewarding conservative generation. We argue that hallucination mitigation should be evaluated as a faithfulness--informativeness--capability trade-off rather than through hallucination scores alone.

Detecting hallucinations in Large Vision-Language Models (LVLMs) requires both accurate span localization and well-calibrated confidence scores. Fine-tuned generative VLMs excel at identifying hallucinated text spans but suffer from overconfidence and high inference latency. Discriminative sequence taggers offer deterministic speed and superior calibration but exhibit conservative span recall. We present SpanCalib-VLM, a hybrid dual-system for the SHROOM-Visions Shared Task that combines a multimodal sequence tagger, consisting of XLM-RoBERTa-Large fused with a SigLIP vision encoder via cross-attention, with our fine-tuned generative VLM (Qwen3.5-4B-SHROOM-SFT). Through a Union-Calibrated Fusion strategy, candidate spans from the generative model are re-scored with calibrated probabilities from the sequence tagger. On the SHROOM-Visions English evaluation split, our ensemble achieves a Pearson calibration correlation of 0.41 and an overall IoU of 0.39, with a clean-response IoU of 0.91} and overall detection accuracy of 70.7%. We make our model weights and code publicly available.

Large Vision-Language Models (LVLMs) integrate visual perception with language generation, enabling responses that span image understanding and complex reasoning. However, LVLMs do not just inherit the text-level hallucinations; they also hallucinate against the image, producing fluent responses ungrounded in what they see. This makes LVLM response scoring inherently harder, and our diagnostics show that existing confidence-based metrics adopted from LLMs are insufficient for LVLMs. Specifically, removing the input image barely changes confidence-based selection, suggesting that output-space confidence primarily captures textual plausibility rather than agreement with the image. To address this gap, we propose LookBack, a training-free LVLM response scoring method that augments token likelihood with visual lookback score, a lightweight measure of how strongly each response token refers to image tokens. Across four benchmarks and three models, LookBack consistently improves Best-of-$N$ selection over existing baselines with negligible additional overhead.

Abstractive text summarization systems frequently generate fluent yet unfaithful summaries by fabricating or distorting relationships between entities and events. Such relation-level hallucinations undermine the reliability of generated summaries, particularly in high-stakes domains. In this work, we present a refined and grounded framework for evaluating relation hallucination in abstractive summarization. We present the empirical Relation Hallucination Index (RHI) by introducing a dependency-aware relation extraction algorithm that incorporates lemmatization-based normalization, named entity grounded subject resolution, passive agent recovery, negation-aware verb modeling, reporting verb filtering, nominal relation fallback, clausal propagation, and systematic deduplication. These enhancements improve the structural fidelity of extracted relation triples and reduce spurious matches during evaluation. In addition, we introduce a normalized formulation of RHI to ensure scale-invariant comparison between datasets and models. The revised metric decomposes hallucination into interpretable components, aggregates relation hallucination metric into a normalized relation faithfulness score. Extensive evaluation across multiple state-of-the-art summarization models demonstrates that the grounded extraction process yields more stable and discriminative hallucination measurements. The proposed framework advances automated relation-level faithfulness evaluation and supports coherence-aware, hallucination-sensitive model analysis.

Large Vision-Language Models (LVLMs) often suffer from object hallucination, generating objects that are absent from the image. Prior work largely attributes this to insufficient visual attention. However, we find that both real and hallucinated objects receive equally strong visual attention in the model's mid-to-late layers, suggesting that the key issue may not be how much the model attends, but what it attends to and why. To this end, we decode the visual features of high-attention regions using Logit Lens, and observe that regions corresponding to real objects can be correctly decoded to the target object tokens, whereas those for hallucinated objects cannot. Building on this, we identify two hallucination mechanisms: (i) visual uncertainty, triggered by semantically similar or confusable regions; masking these regions eliminates the hallucination. (ii) contextual prior, triggered by strong co-occurrence priors; even when the initially attended region is masked, the hallucination persists and attention drifts to other regions. Based on these findings, we propose a simple yet effective training-free Detect-Mitigate framework comprising a Logit-Lens Consistency Check to detect hallucination and targeted remedies: High-Attention Regions Masking (HARM) for visual uncertainty hallucination, and Visual Evidence Enhanced Decoding (VEED) for contextual prior hallucination. Our approach achieves state-of-the-art results on multiple hallucination benchmarks. Code will be available.

Large vision--language models (LVLMs) demonstrate strong multimodal reasoning capabilities but remain prone to hallucination, where model predictions are not grounded in visual evidence. Existing black-box hallucination detection methods estimate uncertainty through a single consistency metric, implicitly assuming that model uncertainty can be adequately characterized by a single measure. However, hallucinations exhibit diverse manifestations of uncertainty across different behavioral probes, making a single measure insufficient to characterize their underlying behavior. We propose \emph{Unique Hallucination Pattern (UHP) Detection}, a fully black-box framework that models hallucination as a structured uncertainty pattern defined by two axes: perturbation modality (image vs.\ text) and logical polarity (a statement vs.\ its negation). Their intersection produces four complementary consistency groups that capture distinct manifestations of model uncertainty, from which both within-group and between-group features are extracted to train a lightweight classifier. Through comprehensive experiments on AMBER and PhD across three LVLMs, UHP Detection consistently outperforms prior black-box and white-box baselines, with improvements of up to $+18.72\%$ AUC-ROC and $+20.07\%$ AUC-PR over the strongest black-box methods. Extensive ablation studies demonstrate that each consistency group contributes complementary information and that their combination forms a structured hallucination pattern. Furthermore, cross-dataset evaluation shows that this learned pattern generalizes across benchmarks, indicating that hallucination behavior reflects a model-specific consistency pattern. \textbf{Code is publicly available at} https://github.com/amirezzati/uhpdet.

Hallucination remains a critical challenge for developing trustworthy Multimodal Large Language Models (MLLMs). While existing benchmarks mainly focus on entity, attribute, and relation hallucinations, knowledge-related failures are often investigated separately, lacking a unified evaluation framework across different hallucination dimensions. To overcome this, we propose \textbf{KnowHal}, a benchmark that explicitly incorporates knowledge hallucination into multimodal hallucination evaluation spanning four dimensions: entity, attribute, relation, and knowledge. KnowHal constructs paired positive and negative questions over shared images and entities, enabling controlled comparisons among perceptual errors, knowledge-related errors, and false-premise acceptance. The benchmark contains 1,800 samples across 10 domains and 50 categories, constructed through a semi-automated pipeline combining LLM assistance, CLIP-based filtering, and human verification. We evaluate 14 representative MLLMs on KnowHal and conduct extensive analyses. Results show that the knowledge dimension consistently presents the greatest challenge for nearly all evaluated models, while most models exhibit substantial performance degradation on negative questions, revealing limited robustness to false premises. By unifying four hallucination dimensions with paired question design, KnowHal addresses an important gap in existing evaluation frameworks and enables a more comprehensive assessment of hallucinations in MLLMs.

Hallucination remains a persistent challenge in generative super-resolution (GSR), where reconstructed results may contain visually plausible yet weakly supported content, structural deviations, or unnatural textures with respect to the low-resolution (LR) input. Existing GSR methods have extensively explored the trade-off between perceptual realism and reconstruction fidelity, but the division between preserving reliable coarse-scale information and restoring more uncertain fine details is often handled implicitly within the overall restoration process. Visual autoregressive (VAR) modeling provides a natural opportunity to revisit this issue, as its coarse-to-fine next-scale prediction offers an explicit scale-wise generation interface. However, existing VAR-based SR methods still inherit the original full 1-to-$N$ autoregressive generation path, even though, for super-resolution, coarse-scale information in LR is often relatively more reliable, while long autoregressive chains may accumulate prediction errors. Motivated by these observations, we propose \textbf{K2N}, which reformulates VAR-based SR from full-path generation into a $k$-to-$N$ detail continuation process. Specifically, early coarse-scale states are established directly from LR, while only the remaining finer scales are restored autoregressively. Experimental results show that K2N remains competitive with the VARSR baseline on standard SR metrics, while exhibiting clearer advantages on hallucination-focused evaluation. These findings suggest that explicitly rethinking the generation path in a scale-wise manner can be a promising direction for improving the reliability of generative super-resolution. Our code will be released soon at https://github.com/BRL-SYSU/K2NSR.

In an age of rapid model turnover, how do we make hallucination evaluation more perennial? We explore whether human-written hallucination samples could take the place of model-generated hallucinations, in order to make benchmarking detection independent of particular models. To this end, we construct a dataset of 1,600 human-written samples, spanning four languages (Chinese, English, French, Italian), and 18,400 samples from five vision-and-language models, all annotated for hallucinations using a fine-grained span-level labeling scheme. We find that human-written samples result in higher agreement and allow greater control of dataset contents, while remaining distributionally similar to samples derived from vision-and-language samples and providing a reasonable portrayal of detection capabilities - suggesting that human data is a viable substitute for model-based hallucination benchmarks.

Language model-based text-to-speech (LM-based TTS) remains vulnerable to speech hallucinations that deviate from the target text. Existing mitigation mainly relies on architectural changes or additional training, while decoding-time control remains underexplored. We present a conditional information view that distinguishes text-derived alignment information from experience information supplied by acoustic context and learned speech regularities. We hypothesize that an important class of hallucinations begins when alignment support is insufficiently reflected in the selected token at a vulnerable transition. Using predictions from the same speech LM with and without text conditions, we propose Experience-Calibrated Contrastive Decoding (ECCD), a training-free method that strengthens alignment support while preserving useful experience information. ECCD preserves the original expert distribution, applies only positive alignment enhancement, and calibrates its strength using set-level experience compatibility. Across four models, ECCD reduces WER/CER by up to 55.6% in all SeedTTS-Eval settings and 24 of 25 multilingual CV3-Eval settings. A listening test yields a CMOS gain of $+0.644$ while retaining strong speaker similarity. Further analysis shows that alignment influence and decision-level gain vary within linguistic units and are lower at first-error boundaries than at matched correct boundaries. Overall, these extensive experiments and analyses identify conditional information control as a promising decoding-time direction for mitigating speech hallucination.

Sentimental Image Captioning (SIC) requires balancing emotional expression with visual fidelity. Existing methods often struggle with this trade-off, leading to hallucinations due to insufficient local grounding and the lack of sentimental verification mechanisms. To address these limitations, we propose SEA-Cap, a Sentiment-Evidence-Aware Multi-Agent System for faithful and evidence-grounded sentimental image captioning. SEA-Cap incorporates a Sentiment Evidence Miner that extracts structured, local affective cues to shift sentiment control from global attributes to verifiable object-level evidence. Leveraging this evidence, our framework orchestrates a collaborative workflow where a Generator, Hallucination Checker, and Arbitrator iteratively refine captions via a shared blackboard. By explicitly auditing generated content against mined visual evidence, SEA-Cap ensures both sentiment accuracy and factual consistency. Extensive experiments on two benchmark datasets demonstrate that SEA-Cap effectively mitigates hallucinations and achieves state-of-the-art performance.

Large Language Models can produce fluent text that is false, unsupported by the available evidence, or inconsistent with information that appears to be internally represented by the model. We study hallucination detection from the geometry of hidden activations and introduce the D-Score, a simple spectral statistic computed from a single forward pass. For a fixed model, layer, and tolerance parameter, the D-Score counts how many singular directions of the hidden activation matrix have singular values that remain close to the leading one. We use this quantity as a hallucination score, classifying an input text as hallucinated when its D-Score is larger than a pre-defined quantity. The motivation is that, when a model processes a text that conflicts with information available in its own internal state, the hidden representation may encode both the asserted content and some form of counter-evidence, uncertainty, correction, or lack of support; this can make the hidden trajectory spread across additional singular directions. We formalize this intuition through a lightweight spectral argument and evaluate the resulting detector on FAVA-Annotation and RAGTruth. The experiments indicate that the D-Score is a strong hidden-state signal for hallucination detection, while requiring no external verifier, no retrieval step, and no multiple generations.

Language generation in the limit is an elegant model introduced by Kleinberg and Mullainathan [KM24] to formally study language generation by an algorithm that learns solely based on example strings. In this model, an algorithm is said to correctly generate from a language if it never makes an error after some finite time. In contrast, even sophisticated language models are known to regularly hallucinate in practice. In this paper, we initiate the study of language generation in the limit with (infinite) hallucination, i.e., the algorithm may generate incorrect strings infinitely often, but the errors occur at a limited rate (possibly even with 0-measure). We first show that hallucination, even at rate 0, makes generation in the limit strictly more powerful: there are language collections that cannot be generated with finite error but can be generated with infinite error, even when errors occur on a 0-measure set of time-steps. Furthermore, while all countable collections are generatable with finite error, we show a strict hierarchy of (uncountable) language collections characterized by the hallucination rate. This hierarchy extends to breadth, the fraction of the target language generated. While all countable collections can attain the optimal breadth of 1/2 [KW26b], we show strict separation at every breadth and hallucination rate. Finally, we study generation in the limit without repetition, where the algorithm may not repeat strings. This lets us compare the sets of correct and incorrect strings generated, rather than the fractions of correct and incorrect time-steps. Once again, we demonstrate a strict hierarchy at every hallucination rate and breadth. Taken together, these results reveal rich structure in language collections generatable in the limit with hallucination and establish hallucination rate as an important parameter in the theoretical study of language generation.

Enterprises will not deploy AI agents they cannot trust, and the most-cited reason for distrust is hallucination: confident, fluent output that is simply not true. The common response is to wait for a model that does not hallucinate. We argue that this is the wrong target. Large language models are, by construction, capable of generating unsupported text, and no amount of scale removes the possibility; a faithfulness judge bolted onto a raw model catches some errors but still ships others, and even well-curated retrieval pipelines have been shown to fabricate citations. We reframe the goal: "zero hallucination" is not a property a model possesses but a property a system enforces. We present HALO (Hallucination-Aware Layered Oversight), an assurance architecture which treats hallucination as a containable failure mode rather than an eliminable one. HALO composes six layers of defense: grounded generation over retrieved, approved content; constrained, deterministic execution that bounds where the model can err; multi-signal verification that scores every output for groundedness and hallucination using both an LLM judge and evidence-based checks against the source text; calibrated abstention, so the system declines rather than guesses when grounding is insufficient; total traceability of every retrieval, tool call, and generation; and continuous oversight that detects drift, alerts on threshold breaches, and closes the loop by regenerating and statistically validating improved agents. We detail each layer, give particular attention to evidence-based confidence (which verifies extractions against the source document rather than trusting the model's self-reported certainty), and illustrate the architecture on a regulated claims-extraction workload.

Large language models can generate polished scientific text that includes unsupported claims, allowing hallucinations to enter the archival record. Assessing this risk via technical statements is difficult and often requires expert judgment, but citations provide a more auditable surface: a reference either resolves to a real scholarly work with compatible authorship, or it does not. We measure citation hallucination in peer-reviewed proceedings using a conservative definition limited to identity-level failures: non-existent works and substantial author-list mismatches. We explicitly exclude ordinary bibliographic drift (e.g., venue/year differences, publication-status updates, minor name variants). To audit citations at scale, we build RefChecker, a verification pipeline that resolves bibliography entries against multiple bibliographic sources and escalates unresolved cases to web-search re-verification. We apply RefChecker to accepted camera-ready papers from ICLR, ICML, NeurIPS, and USENIX Security. Hallucinated citations have entered the archival record. While reference-level rates are usually below 1%, proceedings are large enough that paper-level failures are visible: in 2025, roughly one in twenty NeurIPS and USENIX Security papers contains at least two likely hallucinated academic-paper-like references under our strict definition. We also observe post-ChatGPT increases in several venues, including a tail of papers with 5+ failures in a single bibliography, and likely hallucinated citations even among award-winning papers. These results suggest peer review alone does not reliably enforce citation integrity, yet auditing is tractable (about 0.04$ per paper in one venue-scale scan). We open-source RefChecker for routine, reproducible citation verification before publication (https://github.com/markrussinovich/refchecker).

Multimodal large language models (MLLMs) show strong promise for clinical VQA and radiology report generation, yet inference-time hallucinations still undermine trustworthy use: models can produce fluent conclusions that conflict with imaging evidence. Existing mitigation strategies typically rely on additional training, external retrieval/knowledge bases, or multi-stage post-hoc verification, which increases cost and pipeline complexity and often generalizes poorly across models and tasks.To address this, we propose a holistic, training-free evidence-injection framework that systematically mitigates hallucinations through dual-side evidence injection. By leveraging ROI priors acquired using MedSAM in our implementation, we recalibrate the visual perception trajectory via ROI-guided activation modulation while anchoring the textual reasoning trajectory by mapping anatomical coordinates into discrete semantic tokens as verifiable external memory. Then we introduce a task-aware dynamic router to select modality-specific interventions based on task semantics, balancing perceptual grounding and linguistic fluency. We conduct systematic evaluations on 2 tasks and 5 datasets using \texttt{LLaVA-1.5-7B}, \texttt{LLaVA-Med-1.5-7B}, \texttt{Qwen3-VL-8B/32B}, and \texttt{InternVL-3.5-8B/38B}. Controlled ablations and visualizations further validate the framework, which consistently outperforms baselines across medical benchmarks, improving close-ended accuracy by up to $\sim\mathbf{6}\%\uparrow$ and reducing open-ended hallucinations by $\sim\mathbf{35}\%\downarrow$. The code has been made available on GitHub: \href{https://github.com/Henry991115/SPRG}{\textcolor{blue}{https://github.com/Henry991115/SPRG}}.

Language agents plan by generating not only actions but also implicit predictions of how the world will change. These imagined state updates make agents flexible, but they also create a distinct failure mode: hallucinated state claims can be written into context and propagated across subsequent decisions. In contrast, parametric world models provide measurable transition errors but are often weaker semantic planners. We study this tradeoff in graph-structured planning environments and introduce metrics for agent-world-model error, including hallucinated-state rate, propagation depth, and long-horizon error growth. We then propose Hybrid World-Model Planning (Hybrid-WM), which keeps the language model as the planner while using a small parametric transition model to predict action validity, state deltas, risk, and value. A consistency gate compares the agent's imagined delta with the parametric prediction and triggers targeted revision only under disagreement. Across four graph-structured planning benchmarks, Hybrid-WM improves success while reducing hallucinated state propagation. In live GPT-4o-mini evaluations, it reduces hallucinated-state rate from 0.176 to 0.035; in calibrated simulator ablations, it improves success from 0.668 to 0.838 with modest additional inference. These results suggest that lightweight parametric transition models can serve as effective grounding mechanisms for language-agent planning without replacing semantic reasoning.

Large vision-language models (LVLMs) hallucinate: they assert visual details that the image does not support. A principled remedy is selective prediction with a distribution-free guarantee-verify each claim and abstain when the claim is not grounded, so that the hallucination rate among asserted claims is provably bounded. We show, however, that this guarantee is bought at a brutal price: to keep the hallucination rate below $5\%$ on a balanced object-existence benchmark, a state-of-the-art conformal filter must abstain on more than $80\%$ of claims. We argue that abstention is wasteful when more visual evidence is cheaply available, and introduce Budgeted Conformal Evidence Acquisition (BCEA), which replaces the binary answer/abstain decision with a three-way choice: answer, abstain, or acquire additional visual evidence by re-examining the image (zooming, cropping, or applying a claim-specific intervention) under a bounded compute budget. We make two observations. First, acquisition that is plugged naively into a calibrated filter breaks the statistical guarantee -- realized risk overshoots the target by up to $17$ points -- because the acquisition step destroys the exchangeability that conformal calibration relies on. Second, folding the entire acquisition policy into the score function and re-calibrating on post-acquisition scores \emph{restores} the finite-sample guarantee while still recovering coverage. BCEA further uses structured, claim-type-specific interventions. Across the POPE benchmark and COCO-constructed existence and spatial-relation claims, on four open VLMs, BCEA controls the hallucination rate at the target level and consistently improves coverage over a guaranteed-abstention baseline.

Hallucinations, where language models (LMs) generate factually ungrounded responses, pose serious risks, as users tend to blindly rely on them. This is particularly concerning in high-stakes domains, where consequences of such model behavior can lead to significant harms. Despite notable progress in understanding hallucinations, it remains unclear how reliably these models can recognize the limits of their knowledge. We introduce PhantomBench, the first large-scale benchmark of its kind, comprising more than 60K non-existent terms and entities derived from real concepts across diverse domains. Using our benchmark, we evaluate a total of 21 models of various types and sizes. We show staggering hallucination rates across the board (with average rates as high as 86.7% in some cases), and note that even frontier models surprisingly fail to abstain on non-existent concepts, especially when the input presumes their existence. We then show that PhantomBench can serve as a proxy for studying model behavior on rare concepts for which models are more prone to hallucinate. We also provide a pipeline to construct PhantomBench, enabling scalable generation of non-existent concepts tailored to the specific needs of researchers and practitioners.

As Vision-Language Models are increasingly deployed in safety-critical applications, the trustworthiness of their explanations becomes crucial. Explainable AI (XAI) methods for Vision-Language Models often suffer from semantic hallucination, where attribution maps highlight prominent image regions even when prompted with incorrect text descriptions (e.g., highlighting a dog when prompted ``cat''). Although this problem is widespread, a formal mathematical analysis of XAI methods and CLIP embeddings is largely missing in the literature. We demonstrate that this phenomenon is not specific to a single architecture but is a fundamental consequence of Linear Semantic Leakage in high-dimensional embedding spaces. We propose a unified theoretical framework, Linear Semantic Attribution (LSA), which generalizes across discriminative methods. We introduce OSP, a geometric intervention that utilizes the residual property of OMP to disentangle unique semantic signals from shared concepts. We prove theoretically and demonstrate empirically that OSP minimizes hallucination by orthogonalizing the query vector against distractor concepts, rendering the attribution model blind to shared features while preserving fidelity for correct prompts. Our code is available at: https://github.com/emirhanbilgic/Orthogonal-Semantic-Projection

Recent advancements in Multimodal Large Language Models (MLLMs) have demonstrated remarkable proficiency in open-world reasoning and understanding. However, a critical ambiguity persists: it remains unclear whether these models genuinely synthesize cross-modal information to construct physically grounded reasoning chains, or if they merely exploit strong language priors to mask single-modality reliance, thereby hallucinating advanced multimodal capabilities. Motivated by this, and to rigorously mitigate language modality bias and shortcuts, we propose a novel multimodal Chrono}logical Physical Dynamics Reasoning Benchmark ChronoPhyBench, which unifies next state prediction with Visual Question Answering (VQA) paradigms by conditioning on historical video context and textual captions to enforce models to deduce subsequent physical states through both single image selection and the inherently more complex task of multiple frame chronological sorting. Concurrently, we construct a large-scale multimodal reasoning dataset curated using the ChronoPhyBench criteria, comprising over 10,000 long-form videos paired with meticulously annotated captions, totaling 5M tokens. Our experimental evaluations reveal a stark contrast to conclusions drawn by previous benchmarks. The capacity of current open-source models to perform physically grounded multimodal reasoning remains in its infancy. Ultimately, this work seeks to systematically stress-test the reasoning capabilities of multimodal models, quantify hallucination rates, and advance the development of Physical AI, thereby providing the community with a robust and transparent evaluation framework toward Artificial General Intelligence (AGI).

Small open-source code models that power IDE autocomplete still emit hallucinated Fill-in-the-Middle (FIM) completions: syntactically natural calls to methods, parameters, variables, and imports that do not exist in the surrounding project. Existing mitigations either require per-language execution sandboxes that do not apply at mid-keystroke or preference-optimisation pipelines that need large human-labelled corpora. We propose an execution-free alternative: use frontier code models to synthesise plausible-but-wrong completions as hard negatives, then leverage the contrast between these synthetic hallucinations and the ground-truth developer edit as a supervised fine-tuning signal. Our pipeline scrapes multilingual FIM contexts from public GitHub across eight languages and asks a panel of three frontier generators to produce one hard negative per context for each of four hallucination types drawn from the Delulu taxonomy, a Docker-verified multilingual FIM hallucination benchmark, yielding a paired chosen/rejected dataset. Fine-tuning Qwen2.5-Coder-7B-Instruct on a 100K-row curated subset lifts Delulu exact match by +18.8 points and edit similarity by +0.22 on every language and every type, while also improving every HumanEval-Infilling split and every SAFIM subset. The same recipe at 3B lifts Delulu by +12.8 EM with a small, characterised general-FIM trade-off. Five-axis ablations (size, type mix, language coverage, base-model family, and a difficulty-aware fool rate) plus a head-to-head SFT vs. DPO/ORPO comparison map which design choices drive the gain. We release the full pipeline source code -- generation, fool-rate LLM judging, curation, and the FIM fine-tuning recipe -- so that the experiments in this paper can be reproduced end-to end on any permissively licensed corpus.

Existing hallucination taxonomies classify LLM errors by what is wrong with the output -- memorised misconceptions, reasoning failures, fluent fabrications. These taxonomies are useful for diagnosis but cannot answer a different question: which uncertainty scorer would have caught this error? We propose a complementary taxonomy that classifies errors by their detectability signature -- the signal a scorer family would read. The DECK taxonomy is a 2x2 partition along inter-sample consistency and token-level confidence into four behavioural regimes (Drift, Entrenched, Confabulation, Knotted), each mapping to a specific scorer family (or families) that can detect it: black-box consistency scorers have signal in D and C, white-box token-probability scorers have signal in K and C, and only an LLM-as-a-Judge with independent pretraining can detect E. Cell membership is operationalised by a Youden's J optimal split on each scorer axis. Across three models and four datasets we validate the taxonomy two ways: by analysing scorer-pair disagreement, and by checking that external labels (SelfAware unanswerable, HaluEval adversarial, PopQA entity popularity) land in the predicted DECK cells, with model-scale and content-specific secondary-cell refinements. We further identify a universal blind spot of output-level UQ: on knowledge-gap inputs where the generator emits confident, repeatable fabrications, every output-level family collapses by construction. A linear probe on Llama-3-8B's hidden states also collapses to chance, giving preliminary evidence that the failure may persist at the activation level; richer internal-state methods (UQ heads, information-theoretic estimators) remain to be tested.

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.

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.

Vision-Language Models (VLMs) are becoming the cornerstone of high-level reasoning for robotic automation, enabling robots to parse natural language commands and perceive their environments. However, their susceptibility to hallucinations introduces critical failures in decision-making, posing significant safety and reliability risks in physical deployments. This challenge is exacerbated by the open-ended nature of real-world tasks, where questions vary vastly in difficulty and modality, demanding robust and adaptable reasoning strategies. To tackle this, we propose the Pseudocode-guided Structured Reasoning framework (PStar), which adaptively selects structured pseudocode reasoning paths to help VLMs perform flexible and step-by-step reasoning. We first design a set of abstract reasoning functions and formulate a structured pseudocode library to represent modular reasoning strategies. Crucially, we design a Difficulty Feature Vector (DFV) that allows the model to assess question complexity and adaptively choose appropriate reasoning strategies-enhancing robustness and interpretability. Extensive experiments demonstrate that PStar significantly reduces hallucination rates, achieving state-of-the-art scores of 87.1% on POPE and 68.0% on MMStar, outperforming even GPT-4V. By providing a validated mechanism to reduce visual-language errors, PStar offers a critical step toward deploying more trustworthy and deterministic VLMs for real-world automated systems, where such errors can lead to catastrophic outcomes.

Spracklen et al. (USENIX Security '25) showed that code-generating large language models hallucinate package names that do not exist on PyPI or npm at rates ranging from 5.2% on commercial models to 21.7% on open-source models, creating an attack surface for slopsquatting -- the registration of malicious packages under hallucinated names. We replicate their methodology on five frontier code-capable LLMs released between October 2025 and March 2026: Claude Sonnet 4.6, Claude Haiku 4.5, GPT-5.4-mini, Gemini 2.5 Pro, and DeepSeek V3.2. Across 199,845 paired Python and JavaScript prompts validated against PyPI and npm master lists, we measure overall hallucination rates between 4.62% (Claude Haiku 4.5) and 6.10% (GPT-5.4-mini) -- an order-of-magnitude compression of the inter-model spread observed by Spracklen, but not a retirement of the threat. Beyond replication, we identify a set of 127 package names (109 on PyPI, 18 on npm) that all five evaluated models invent identically; following coordinated disclosure with PyPI Security and Socket.dev, 53 of these (41 on PyPI, 12 on npm) remain registrable by an attacker after each registry's existing defenses, constituting a model-agnostic supply-chain attack surface that no single-model study can reveal. We further document a Python-over-JavaScript hallucination asymmetry that inverts Spracklen's 2024 finding, identify a Haiku-below-Sonnet inversion within the Anthropic family, and observe a Jaccard-similarity peak between DeepSeek V3.2 and GPT-5.4-mini (J = 0.343) suggestive of shared training-data origins.

Artificial intelligence (AI) has transformed imaging inverse problems, from medical diagnostics to Earth observation. Yet deep neural networks can produce hallucinations, realistic-looking but incorrect details, undermining their reliability, especially when ground truth data is unavailable. We develop a theoretical framework showing that such hallucinations are not merely artifacts of particular models, but can arise from the ill-posed nature of the inverse problem itself. We derive necessary and sufficient conditions for hallucinations, together with computable bounds on their magnitude that depend only on the forward model. Building on this theory, we introduce algorithms to: (1) estimate the minimum hallucination magnitude achievable by any reconstruction model for a given input; (2) assess the faithfulness of reconstructed details by a given reconstruction model. Experiments across three imaging tasks demonstrate that our approach applies broadly, including to modern generative models, and provides a principled way to quantify and evaluate AI hallucinations.

Large language models (LLMs) are increasingly used to translate natural-language optimization problems into mathematical formulations and solver code, but matching the reference objective value is not a reliable test of correctness: an artifact may agree numerically while still changing the underlying optimization semantics. We formulate this issue as \emph{optimization-modeling hallucination detection}, namely structural consistency auditing over the problem description, symbolic model, and solver implementation. We develop, to our knowledge, the first fine-grained hallucination taxonomy specifically for optimization modeling, spanning objective, variable, constraint, and implementation failures. We use this taxonomy to design OptArgus, a multi-agent detector with conductor routing, specialist auditors, and evidence consolidation. To evaluate this setting, we introduce a three-part benchmark suite with $484$ clean artifacts, $1266$ controlled injected artifacts, and $6292$ natural LLM-generated artifacts. Against a matched single-agent baseline, OptArgus produces fewer false alarms on clean artifacts, more accurate top-ranked localization on controlled single-error cases, and stronger detection on natural model outputs. Together, these contributions turn optimization-modeling hallucination detection into a concrete empirical problem and suggest that modular, taxonomy-grounded auditing is a practical route to more reliable optimization modeling.

Large vision-language models (VLMs) demonstrate strong performance in medical image understanding, but frequently generate clinically plausible yet incorrect statements, raising significant safety concerns. Existing medical hallucination benchmarks primarily focus on 2D imaging with one-shot diagnostic questions, offering limited insight into whether predictions are grounded in correct localization and abnormality identification, allowing critical reasoning errors to remain hidden behind seemingly correct diagnoses. We introduce Med-StepBench, the first large-scale benchmark for step-wise hallucination detection in 3D oncological PET/CT, comprising over 12,000 images and more than 1,000,000 image-statement pairs across volumetric and multi-view 2D data, which decomposes clinical reasoning into four expert-designed diagnostic stages. Using clinician-verified annotations, we perform the first step-level evaluation of general-purpose and medical VLMs, revealing systematic failure modes obscured by aggregate accuracy metrics. Furthermore, we show that current VLMs are highly susceptible to adversarial yet clinically plausible intermediate explanations, which significantly amplify hallucinations despite contradictory visual evidence. Together, our findings highlight fundamental limitations in grounding multi-step clinical reasoning and establish Med-StepBench as a rigorous benchmark for developing safer and more reliable medical VLMs.

Large Language Models for code generation frequently produce hallucinations in Fill-in-the-Middle (FIM) tasks -- plausible but incorrect completions such as invented API methods, invalid parameters, undefined variables, or non-existent imports. These failures pass superficial review yet introduce runtime errors. We introduce Delulu, a verified multi-lingual benchmark of 1,951 FIM samples across 7 languages and 4 hallucination types. Samples are curated through an adversarial pipeline: a frontier LLM generates plausible hallucinations, four diverse judge models evaluate them, embedding-based clustering mines progressively harder examples, self-contained Docker containers verify that golden completions compile while hallucinated variants produce the expected runtime error, and a final human-expert review removes any remaining biased or trivially decidable samples. We evaluate 11 open-weight FIM models from five families spanning 0.5B-32B parameters: a six-point Qwen2.5-Coder scaling slate, plus a cross-family slate (CodeLlama, DeepSeek-Coder-V2, StarCoder2). The strongest model reaches only 84.5% pass@1, no family exceeds 0.77 Edit Similarity, and every family produces hallucination-aligned completions on a non-trivial share of samples, confirming that the difficulty exposed by Delulu is task-intrinsic rather than family-specific. We release the benchmark, containers, and evaluation framework at https://github.com/microsoft/delulu.

Large Language models (LLMs) show extraordinary abilities, but they are still prone to hallucinations, especially when we use them for generating Academic content. We have investigated four popular LLMs, ChatGPT, Grok, Gemini, and Copilot for hallucinations specifically for academic writing. We have designed 80 prompts across four categories, namely, reference generation, factual explanation, abstract generation, and writing improvement. We evaluated the model using a 0-5 rubric score, which checks factual accuracy, reference validity, coherence, style consistency, and academic tone. A novel weighted metric, Hallucination Index (HI), was introduced to measure hallucination in the responses generated by the models. Some of the most widely used evaluation metrics often fail to check errors which alter sentiment in machine-translated text. We found that Grok and Copilot perform better on reference generation tasks, but they often struggle with abstract or stylistic prompts, with HI values of 0.67 and 0.70, respectively. Whereas, Gemini and ChatGPT have done well with having stronger tone control, but they lack in writing factual tasks and higher hallucination risk with HI scores of 0.53 and 0.57, respectively. Our study found that hallucination behavior does not depend solely on model architecture but also on the type of task and the prompting conditions we are providing. We propose that our work opens new research dimensions for future researchers.

Diffusion large language models generate text through iterative denoising, exposing hidden trajectories that may contain reliability signals beyond the final output. We propose HIVE, which compresses trajectory hidden states, selects informative step-layer evidence, and conditions a verifier through continuous prefix embeddings to produce a hallucination score and structured diagnostics. Across two D-LLMs and three QA benchmarks, HIVE outperforms eight established baselines and a verifier-backbone-matched text-only control in all six settings. Relative to text-only verification, hidden-evidence conditioning improves AUROC by 1.73--4.60 points and AUPRC by 1.10--3.62 points, with average gains of 3.15 and 2.28 points, respectively. Ablations, evidence interventions, and cross-dataset transfer further support the complementary value of fine-grained hidden trajectory evidence.

Egocentric videos provide a distinctive setting in which sound serves as crucial cues to understand user activities and surroundings, particularly when visual information is unstable or occluded due to continuous camera movement. State-of-the-art large audio-visual language models (AV-LLMs) can generate multimodal descriptions. However, we show in this work that they are prone to audio hallucinations, often inferring sounds from visual cues that are visible but not heard. We present a systematic and automatic evaluation framework for analyzing audio hallucinations in egocentric video through a targeted question-answering (Q/A) protocol. We curate a dataset of 300 egocentric videos and design 1,000 sound-focused questions to probe model outputs. To characterize hallucinations, we propose a grounded taxonomy that distinguishes between foreground action sounds from the user activities and background ambient sounds. Our evaluation shows that advanced AV-LLMs, such as Qwen2.5 Omni, exhibit high hallucination rates, achieving only 27.3% and 39.5% accuracy on Q/As related to foreground and background sounds, respectively. With this work, we highlight the need to measure the reliability of multimodal responses, emphasizing that robust evaluation of hallucinations is essential to develop reliable AV-LLMs.

Large Language Models (LLMs) frequently hallucinate, limiting their reliability in critical applications. Conformal Prediction (CP) addresses this by calibrating error rates on held-out data to provide statistically valid confidence guarantees. Recent work extends CP to LLM factuality to filter out risky claims, ensuring that hallucination rates remain below a user-specified level (e.g., 10%). While prior methods treat claims independently, Coherent Factuality extends to multi-step reasoning by representing outputs as dependency graphs and jointly validating claims with their logical ancestors. A key limitation is that Coherent Factuality is not differentiable, requiring hand-crafted scorers that at high reliability levels remove nearly 60% of true claims. We introduce Differentiable Coherent Factuality (DCF), a fully differentiable relaxation that enables learning improved scorers while provably recovering the original algorithm's guarantees. Experiments on two benchmark reasoning datasets demonstrate DCF achieves up to 141% improvement in claim retention while maintaining reliability guarantees, representing a significant step towards reliable conformal LLM systems.

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.

Vision-Language Models (VLMs) are increasingly deployed in settings where reliable visual grounding carries operational consequences, yet their behavior under progressively coercive prompt phrasing remains undercharacterized. Existing hallucination benchmarks predominantly rely on neutral prompts and binary detection, leaving open how both the incidence and the intensity of fabrication respond to graded linguistic pressure across structurally distinct task types. We present Ghost-100, a procedurally constructed benchmark of 800 synthetically generated images spanning eight categories across three task families: text-illegibility, time-reading, and object-absence, each designed under a negative-ground-truth principle that guarantees the queried target is absent, illegible, or indeterminate by construction. Every image is paired with five prompts drawn from a structured 5-Level Prompt Intensity Framework, holding the image and task identity fixed while varying only directive force, so that tone is isolated as the sole independent variable. We adopt a dual-track evaluation protocol: a rule-based H-Rate measuring the proportion of responses in which a model crosses from grounded refusal into unsupported positive commitment, and a GPT-4o-mini-judged H-Score on a 1-5 scale characterizing the confidence and specificity of fabrication once it occurs. We additionally release a three-stage automated validation workflow, which retrospectively confirms 717 of 800 images as strictly compliant. Evaluating nine open-weight VLMs, we find that H-Rate and H-Score dissociate substantially across model families, reading-style and presence-detection subsets respond to prompt pressure in qualitatively different ways, and several models exhibit non-monotonic sensitivity peaking at intermediate tone levels: patterns that aggregate metrics obscure.

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.

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.

Evaluating large language models (LLMs) for clinical documentation tasks such as SOAP note generation remains challenging. Unlike standard summarization, these tasks require clinical abstraction, normalization of colloquial language, and medically grounded inference. However, prevailing evaluation methods including automated metrics and LLM as judge frameworks rely on lexical faithfulness, often labeling any information not explicitly present in the transcript as hallucination. We show that such approaches systematically misclassify clinically valid outputs as errors, inflating hallucination rates and distorting model assessment. Our analysis reveals that many flagged hallucinations correspond to legitimate clinical transformations, including synonym mapping, abstraction of examination findings, diagnostic inference, and guideline consistent care planning. By aligning evaluation criteria with clinical reasoning through calibrated prompting and retrieval grounded in medical ontologies we observe a significant shift in outcomes. Under a lexical evaluation regime, the mean hallucination rate is 35%, heavily penalizing valid reasoning. With inference aware evaluation, this drops to 9%, with remaining cases reflecting genuine safety concerns. These findings suggest that current evaluation practices over penalize valid clinical reasoning and may measure artifacts of evaluation design rather than true errors, underscoring the need for clinically informed evaluation in high context domains like medicine.

Hallucinations remain a major obstacle for large language models (LLMs), especially in safety-critical domains. We present HALT (Hallucination Assessment via Log-probs as Time series), a lightweight hallucination detector that leverages only the top-20 token log-probabilities from LLM generations as a time series. HALT uses a gated recurrent unit model combined with entropy-based features to learn model calibration bias, providing an extremely efficient alternative to large encoders. Unlike white-box approaches, HALT does not require access to hidden states or attention maps, relying only on output log-probabilities. Unlike black-box approaches, it operates on log-probs rather than surface-form text, which enables stronger domain generalization and compatibility with proprietary LLMs without requiring access to internal weights. To benchmark performance, we introduce HUB (Hallucination detection Unified Benchmark), which consolidates prior datasets into ten capabilities covering both reasoning tasks (Algorithmic, Commonsense, Mathematical, Symbolic, Code Generation) and general purpose skills (Chat, Data-to-Text, Question Answering, Summarization, World Knowledge). While being 30x smaller, HALT outperforms Lettuce, a fine-tuned modernBERT-base encoder, achieving a 60x speedup gain on HUB. HALT and HUB together establish an effective framework for hallucination detection across diverse LLM capabilities.

Empowered by large language models (LLMs), intelligent agents have become a popular paradigm for interacting with open environments to facilitate AI deployment. However, hallucinations generated by LLMs-where outputs are inconsistent with facts-pose a significant challenge, undermining the credibility of intelligent agents. Only if hallucinations can be mitigated, the intelligent agents can be used in real-world without any catastrophic risk. Therefore, effective detection and mitigation of hallucinations are crucial to ensure the dependability of agents. Unfortunately, the related approaches either depend on white-box access to LLMs or fail to accurately identify hallucinations. To address the challenge posed by hallucinations of intelligent agents, we present HalMit, a novel black-box watchdog framework that models the generalization bound of LLM-empowered agents and thus detect hallucinations without requiring internal knowledge of the LLM's architecture. Specifically, a probabilistic fractal sampling technique is proposed to generate a sufficient number of queries to trigger the incredible responses in parallel, efficiently identifying the generalization bound of the target agent. Experimental evaluations demonstrate that HalMit significantly outperforms existing approaches in hallucination monitoring. Its black-box nature and superior performance make HalMit a promising solution for enhancing the dependability of LLM-powered systems.

Large language models (LLMs) increasingly generate citation-backed responses, yet citation hallucination remains a major challenge for trustworthy scientific information access. We introduce REASONS, a benchmark of 12,723 sentence-level citation instances spanning 12 arXiv subject categories, designed to evaluate scientific citation attribution under varying evidence conditions. We propose a dual-metric framework consisting of Abstention Rate (AR) and Hallucination Rate (HR) to characterize the trade-off between reliability and responsiveness. Using author-attribution and title-attribution tasks, we evaluate proprietary and open-source LLMs under zero-context, metadata-augmented, cascaded metadata-augmented prompting (CMP), retrieval-augmented, and adversarial settings. Advanced RAG lowers HR relative to Naive RAG (65.4% vs. 87.6%) but reduces AR from 5.0% to 0%. Under adversarial metadata, several systems exceed 85% HR, while retrieval-augmented variants frequently maintain near-zero abstention. Human evaluation of 1,000 outputs ($κ=0.78$) finds a 12.7:1 ratio of factual hallucinations to acceptable paraphrases. Our findings demonstrate that citation attribution systems should be evaluated not only for correctness but also for their ability to abstain appropriately under uncertainty. REASONS provides a benchmark and evaluation framework for studying attribution reliability in citation generation.