Mitigation

Generative retrieval (GR) ranks documents by autoregressively generating document identifiers. Because many GR methods rely on trie-constrained beam search, they are vulnerable to early pruning of relevant prefixes under finite-beam decoding. Planning Ahead in Generative Retrieval (PAG) mitigates this failure mode by using simultaneous decoding to compute a document-level look-ahead prior that guides subsequent sequential decoding. We reproduce PAG at inference time and stress-test its decoding behavior. Using the authors' released checkpoint and identifier/trie artifacts under the reported decoding setup, we reproduce the main effectiveness results on MS MARCO Dev and TREC-DL 2019/2020, and corroborate the reported beam-size-latency trade-off in our hardware setting. Beyond reproduction, we introduce plan drift diagnostics that quantify how intent-preserving query variations alter the planner's top-n candidate set and highest-weight planner tokens, and how these changes affect guided decoding. We find that PAG's planning signal is brittle under lexical surface-form variation: intent-preserving typos can trigger plan collapse, where the planned candidate pool shifts enough that the look-ahead bonus provides little useful guidance, effectively reverting decoding toward weaker unguided search. We further evaluate fixed-index cross-lingual robustness using non-English mMARCO queries against an English index, and assess query-side mitigation strategies that require no re-indexing; query translation provides the strongest recovery in our setting. Overall, our results confirm PAG's reported effectiveness and the benefit of planning-guided decoding under the released inference setup, while showing that these gains depend on the stability of the planning signal under realistic query variation and query-document mismatch.

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.

This paper investigates communication-efficient neural network transmission by exploiting structured symmetry constraints in convolutional kernels. Instead of transmitting all model parameters, we propose a degrees-of-freedom (DoF) based codec that sends only the unique coefficients implied by a chosen symmetry group, enabling deterministic reconstruction of the full weight tensor at the receiver. The proposed framework is evaluated under quantization and noisy channel conditions across multiple symmetry patterns, signal-to-noise ratios, and bit-widths. To improve robustness against transmission impairments, a projection step is further applied at the receiver to enforce consistency with the symmetry-invariant subspace, effectively denoising corrupted parameters. Experimental results on MNIST and CIFAR-10 using a DeepCNN architecture demonstrate that DoF-based transmission achieves substantial bandwidth reduction while preserving significantly higher accuracy than pruning-based baselines, which often suffer catastrophic degradation. Among the tested symmetries, \textit{central-skew symmetry} consistently provides the best accuracy-compression tradeoff, confirming that structured redundancy can be leveraged for reliable and efficient neural model delivery over constrained links.

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.

Quantum error mitigation (QEM) provides a practical route for estimating reliable observables on noisy intermediate-scale quantum (NISQ) devices. Traditional QEM strategies, including zero-noise extrapolation (ZNE) and Clifford data regression (CDR), rely on noise scaling or global regression, and their performance is constrained by the exponential growth of the system degrees of freedom. We construct a graph-enhanced mitigation (GEM) framework, which incorporates physical information into the model representation. In this work, quantum circuits are encoded as attributed graphs. Hardware-level physical information is mapped to node and edge features: local noise parameters such as calibration parameters $T_1$, $T_2$, and readout errors are encoded at nodes, while coupling-related information such as two-qubit gate errors is encoded as edge features. Graph neural networks are used to model how errors propagate along the physical coupling structure and build up into non-local correlations. This allows the model to capture local interactions and part of the resulting non-local correlations across qubits. A dual-branch affine correction is applied to maintain consistency with physical constraints. Experiments on 10-qubit and 16-qubit random circuits executed on superconducting quantum processors show that GEM provides a level of accuracy comparable to CDR at small scales, while yielding lower mean absolute error and improved stability in zero-shot transfer to larger systems. Results of the traditional QEM strategy indicate that global regression methods remain effective in low-dimensional settings but become less reliable as system degrees of freedom grow. In contrast, GEM makes use of local physical structures to show better scalability and generalization, while preserving the overall error propagation patterns. This work provides a practical scalable approach to QEM for NISQ devices.

We study how informal surface forms degrade NLI accuracy in ELECTRA-small (14M) and RoBERTa-large (355M) across four transforms applied to SNLI and MultiNLI: slang substitution, emoji replacement, Gen-Z filler tokens, and their combination. Slang substitution (replacing formal words with informal equivalents, e.g., "going to" -> "gonna", "friend" -> "homie") causes minimal degradation (at most 1.1pp): slang vocabulary falls largely within WordPiece coverage, so the tokenizer handles it without signal loss. Emoji replaces content words with Unicode characters that ELECTRA's WordPiece tokenizer maps to [UNK], destroying the input signal before any learned parameters see it (93.6% of emoji examples contain at least one [UNK], mean 2.91 per example). Noise tokens (no cap, deadass, tbh) are fully in-vocabulary but absent from NLI training data, consistent with the model assigning them inferential weight they do not carry. The two failure modes respond to different interventions: preprocessing recovers emoji accuracy by normalizing text before tokenization; augmentation handles noise by exposing the model to noise-bearing examples during training. A hybrid of both achieves 88.93% on the combined variant for ELECTRA on SNLI (up from 75.88%), with no statistically significant drop on clean text. Against GPT-4o-mini zero-shot, unmitigated ELECTRA is significantly worse on transformed variants (p < 0.0001); hybrid ELECTRA surpasses it across all SNLI variants and reaches statistical parity on MultiNLI.

Prompt-induced cognitive biases are changes in a general-purpose AI (GPAI) system's decisions caused solely by biased wording in the input (e.g., framing, anchors), not task logic. In software engineering (SE) decision support (where problem statements and requirements are natural language) small phrasing shifts (e.g., popularity hints or outcome reveals) can push GPAI models toward suboptimal decisions. We study this with PROBE-SWE, a dynamic benchmark for SE that pairs biased and unbiased versions of the same SE dilemmas, controls for logic and difficulty, and targets eight SE-relevant biases (anchoring, availability, bandwagon, confirmation, framing, hindsight, hyperbolic discounting, overconfidence). We ask whether prompt engineering mitigates bias sensitivity in practice, focusing on actionable techniques that practitioners can apply off-the-shelf in real environments. Testing common strategies (e.g., chain-of-thought, self-debiasing) on cost-effective GPAI systems, we find no statistically significant reductions in bias sensitivity on a per-bias basis. We then adopt a Prolog-style view of the reasoning process: solving SE dilemmas requires making explicit any background axioms and inference assumptions (i.e., SE best practices) that are usually implicit in the prompt. So, we hypothesize that bias-inducing features short-circuit assumption elicitation, pushing GPAI models toward biased shortcuts. Building on this, we introduce an end-to-end method that elicits best practices and injects axiomatic reasoning cues into the prompt before answering, reducing overall bias sensitivity by 51% on average (p < .001). Finally, we report a thematic analysis that surfaces linguistic patterns associated with heightened bias sensitivity, clarifying when GPAI use is less advisable for SE decision support and where to focus future countermeasures.

Dynamic 3D Gaussian Splatting methods achieve strong training-view PSNR on monocular video but generalize poorly: on the D-NeRF benchmark we measure an average train-test PSNR gap of 6.18 dB, rising to 11 dB on individual scenes. We report two findings that together account for most of that gap. Finding 1 (the role of splitting). A systematic ablation of the Adaptive Density Control pipeline (split, clone, prune, frequency, threshold, schedule) shows that splitting is responsible for over 80% of the gap: disabling split collapses the cloud from 44K to 3K Gaussians and the gap from 6.18 dB to 1.15 dB. Across all threshold-varying ablations, gap is log-linear in count (r = 0.995, bootstrap 95% CI [0.99, 1.00]), which suggests a capacity-based explanation. Finding 2 (the role of deformation coherence). We show that the capacity explanation is incomplete. A local-smoothness penalty on the per-Gaussian deformation field -- Elastic Energy Regularization (EER) -- reduces the gap by 40.8% while growing the cloud by 85%. Measuring per-Gaussian strain directly on trained checkpoints, EER reduces mean strain by 99.72% (median 99.80%) across all 8 scenes; on 8/8 scenes the median Gaussian under EER is less strained than the 1st-percentile (best-behaved) Gaussian under baseline. Alongside EER, we evaluate two further regularizers: GAD, a loss-rate-aware densification threshold, and PTDrop, a jitter-weighted Gaussian dropout. GAD+EER reduces the gap by 48%; adding PTDrop and a soft growth cap reaches 57%. We confirm that coherence generalizes to (a) a different deformation architecture (Deformable-3DGS, +40.6% gap reduction at re-tuned lambda), and (b) real monocular video (4 HyperNeRF scenes, reducing the mean PSNR gap by 14.9% at the same lambda as D-NeRF, with near-zero quality cost). The overfitting in dynamic 3DGS is driven by incoherent deformation, not parameter count.

Transformers commonly exhibit an attention sink: disproportionately high attention to the first position. We study this behavior in GPT-2-style models with learned query biases and absolute positional embeddings. Combining structural analysis with causal interventions, validated across natural-language, mathematical, and code inputs, we find that the sink arises from the interaction among (i) a learned query bias, (ii) the first-layer MLP transformation of the positional encoding, and (iii) structure in the key projection. Crucially, each component we identify is individually dispensable: architectures omitting each of them robustly exhibit sinks. This indicates that attention sinks may arise through distinct circuits across architectures. These findings inform mitigation of sinks, and motivate broader investigation into why sinks emerge.

Large language models (LLMs) increasingly serve as automated evaluators, yet they suffer from "self-preference bias": a tendency to favor their own outputs over those of other models. This bias undermines fairness and reliability in evaluation pipelines, particularly for tasks like preference tuning and model routing. We investigate whether lightweight steering vectors can mitigate this problem at inference time without retraining. We introduce a curated dataset that distinguishes self-preference bias into justified examples of self-preference and unjustified examples of self-preference, and we construct steering vectors using two methods: Contrastive Activation Addition (CAA) and an optimization-based approach. Our results show that steering vectors can reduce unjustified self-preference bias by up to 97%, substantially outperforming prompting and direct preference optimization baselines. Yet steering vectors are unstable on legitimate self-preference and unbiased agreement, implying self-preference spans multiple or nonlinear directions. This underscores both their promise and limits as safeguards for LLM-as-judges and motivates more robust interventions.

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.

Continual post-training (CPT) is a popular and effective technique for adapting foundation models like multimodal large language models to ever-evolving downstream tasks. While existing research primarily focuses on methods like data replay, model expansion, or parameter regularization, the fundamental role of the learning paradigm remains largely unexplored. This paper presents a comparative analysis of two core post-training paradigms: supervised fine-tuning (SFT) and reinforcement fine-tuning (RFT), investigating their respective impacts on knowledge retention during CPT. Our experiments are conducted across multiple multimodal tasks, utilizing Qwen2.5-VL-7B-Instruct as the base model. The investigation yields two significant findings: (1) When continuously learning on downstream tasks, SFT leads to catastrophic forgetting of previously learned tasks. In contrast, RFT inherently preserves prior knowledge and achieves performance comparable to multi-task training. (2) RFT successfully protects and even enhances the model's general knowledge on standard benchmarks, while SFT degrades general model capabilities severely. Further analysis reveals that this stability is not primarily due to explicit mechanisms like KL penalty or chain-of-thought reasoning. We investigate RFT's learning dynamics and find that its selective update mechanism inherently prevents interference with established knowledge. Based on this insight, we propose a rollout-based instance filtering algorithm (RIF-RFT) that enhances the training efficiency of RFT by focusing on learnable samples. Our comprehensive study demonstrates the superiority of RFT as a robust paradigm for continual post-training.

Data imbalance persists as a pervasive challenge in regression tasks, introducing bias in model performance and undermining predictive reliability. This is particularly detrimental in applications aimed at predicting rare events that fall outside of the domain of the bulk of the training data. In this study, we review the current state-of-the-art regarding sampling-based methods and cost-sensitive learning. Additionally, we propose novel approaches to mitigate model bias. To better assess the importance of data, we introduce the density-distance and density-ratio relevance functions, which effectively integrate empirical frequency of data with domain-specific preferences, offering enhanced interpretability for end-users. Furthermore, we present advanced mitigation techniques (cSMOGN and crbSMOGN), which build upon and improve existing sampling methods. In a quantitative evaluation, we benchmark state-of-the-art methods on 10 synthetic and 42 real-world datasets, using neural networks, XGBoosting trees and Random Forest models. Our analysis shows that while most strategies improve performance on rare samples, they degrade it on frequent ones. The trade-off becomes larger the more the performance on rare samples is increased. However, to reduce this effect we demonstrate that constructing an ensemble of models -- one trained with imbalance mitigation and another without -- can be used. The key findings underscore the superior performance of our novel crbSMOGN sampling technique with the density-ratio relevance function for neural networks, outperforming state-of-the-art methods.

As AI-generated content increasingly populates the web, generative AI models are at growing risk of being trained on their own outputs, a process known as AI autophagy. This feedback loop has been shown to induce model collapse, typically characterized by a loss of diversity in generated content. However, existing work offers a limited understanding of this phenomenon and relies on mitigation strategies that assume access to human-authored data. In this paper, we conduct extensive simulations across multiple datasets and LLMs to address key gaps in the study of model collapse. First, we introduce model-intrinsic measures based on next-token probability distributions, showing that model collapse corresponds to an increasing concentration of probability mass on a small set of tokens. Second, we demonstrate that model collapse is also associated with a loss of common sense, as measured by a decline in commonsense inference accuracy. Third, we identify perplexity (a measure of model "surprise") as a key driver of collapse: fine-tuning on the least "surprising" documents leads to more severe degeneration. Building on this insight, we propose a perplexity-based filtering strategy that prioritizes high-surprise documents during fine-tuning. Unlike existing approaches, our method does not require distinguishing between human-authored and AI-generated content. Across datasets and LLM families, this strategy consistently mitigates model collapse, achieving performance comparable to, and in some cases better than, human-data baselines, while substantially reducing the concentration of next-token probabilities. Overall, our results provide a unified, model-centric understanding of model collapse and suggest practical, scalable strategies for training generative AI systems in increasingly synthetic environments.

Clinical trials bridge basic research and clinical application, serving as essential steps in drug development. This review examines clinical trial phases (Phase I [safety assessment], Phase II [efficacy evaluation], Phase III [large-scale validation], and Phase IV [post-marketing surveillance]), highlighting the distinct characteristics and interconnections. Major challenges are identified, including ethical compliance, participant recruitment, and ensuring diversity and representativeness in trial populations, while proposing evidence-based mitigation strategies. To address these challenges, innovative technologies, such as artificial intelligence, big data analytics, and digital health tools, are transforming trial design and implementation, enhancing efficiency and data quality. Looking forward, the review explores how emerging therapies, including gene therapy and immunotherapy, are reshaping trial design requirements and emphasizes the growing importance of regulatory harmonization and global collaboration. Clinical trials remain central to advancing innovative drug development and improving patient outcomes.