LLM Reliability

LLM: Large Language Model

Ask about this topic

Overview

It asks not only whether a model gets an answer right, but whether it knows when it may be wrong, follows constraints, uses evidence faithfully, and behaves consistently across repeated or multi-turn use. Researchers test these properties with adversarial and perturbation benchmarks, repeated-run and cross-language evaluations, domain-specific tasks, and audits of LLM judges and tool-using agents. Common approaches include estimating uncertainty from logits, hidden representations, or response agreement; selective abstention and conformal calibration; retrieval and symbolic verification; and training methods that reward grounded answers, correction, or hesitation. The central tension is that benchmark accuracy and verbal confidence often fail to predict reliability on individual cases, long tasks, or shifted inputs, while stronger checks and abstention trade coverage, latency, and cost for safer decisions.

Latest papers

CardsList

802 papers116 papers in the last four weeks, up 18% on the four weeks before. 0.7% of all new papers.

Feb 22, 2026

Evaluating the Reliability of Digital Forensic Evidence Discovered by Large Language Model: A Case Study

The growing reliance on AI-identified digital evidence raises significant concerns about its reliability, particularly as large language models (LLMs) are increasingly integrated into forensic investigations. This paper proposes a structured framework that automates forensic artifact extraction, refines data through LLM-driven analysis, and validates results using a Digital Forensic Knowledge Graph (DFKG). Evaluated on a 13 GB forensic image dataset containing 61 applications, 2,864 databases, and 5,870 tables, the framework ensures artifact traceability and evidentiary consistency through deterministic Unique Identifiers (UIDs) and forensic cross-referencing. We propose this methodology to address challenges in ensuring the credibility and forensic integrity of AI-identified evidence, reducing classification errors, and advancing scalable, auditable methodologies. A comprehensive case study on this dataset demonstrates the framework's effectiveness, achieving over 95 percent accuracy in artifact extraction, strong support of chain-of-custody adherence, and robust contextual consistency in forensic relationships. Key results validate the framework's ability to enhance reliability, reduce errors, and establish a legally sound paradigm for AI-assisted digital forensics.

Jeel Piyushkumar Khatiwala, Daniel Kwaku Ntiamoah Addai, Weifeng Xu

School of Criminal Justice, College of Public Affairs, University of Baltimore, Maryland, USA

Digital ForensicsLLM Reliability
AskPDF
Feb 21, 2026

TRUE: A Trustworthy Unified Explanation Framework for Large Language Model Reasoning

Large language models (LLMs) have demonstrated strong capabilities in complex reasoning tasks, yet their decision-making processes remain difficult to interpret. Existing explanation methods often lack trustworthy structural insight and are limited to single-instance analysis, failing to reveal reasoning stability and systematic failure mechanisms. To address these limitations, we propose the Trustworthy Unified Explanation Framework (TRUE), which integrates executable reasoning verification, feasible-region directed acyclic graph (DAG) modeling, and causal failure mode analysis. At the instance level, we redefine reasoning traces as executable process specifications and introduce blind execution verification to assess operational validity. At the local structural level, we construct feasible-region DAGs via structure-consistent perturbations, enabling explicit characterization of reasoning stability and the executable region in the local input space. At the class level, we introduce a causal failure mode analysis method that identifies recurring structural failure patterns and quantifies their causal influence using Shapley values. Extensive experiments across multiple reasoning benchmarks demonstrate that the proposed framework provides multi-level, verifiable explanations, including executable reasoning structures for individual instances, feasible-region representations for neighboring inputs, and interpretable failure modes with quantified importance at the class level. These results establish a unified and principled paradigm for improving the interpretability and reliability of LLM reasoning systems.

Yujiao Yang

Dalian University of Technology, Dalian, China

LLM InterpretabilityFaithfulness of Language Model ExplanationsLLM ReliabilityReasoning Consistency in Language Models
AskPDF
Feb 21, 2026

Think2^{2}: Grounded Metacognitive Reasoning in Large Language Models

Large Language Models (LLMs) demonstrate strong reasoning performance, yet their ability to reliably monitor, diagnose, and correct their own errors remains limited. We introduce a psychologically grounded metacognitive framework that operationalizes Ann Brown's regulatory cycle (Planning, Monitoring, and Evaluation) as a structured prompting architecture, and study its integration within a lightweight dual-process MetaController for adaptive effort allocation. Across diverse reasoning and diagnostic benchmarks (GSM8K, CRUXEval, MBPP, AIME, CorrectBench, and TruthfulQA) using Llama-3 and Qwen-3 (8B), explicit regulatory structuring substantially improves error diagnosis and yields a threefold increase in successful self-correction. Blinded human evaluations over 580 query pairs show an 84% aggregate preference for trustworthiness and metacognitive self-awareness over standard and Chain-of-Thought baselines. Grounding LLM reasoning in established cognitive theory offers a principled path toward more transparent and diagnostically robust AI systems.

Abraham Paul Elenjical, Vivek Hruday Kavuri, Vasudeva Varma

IIIT Hyderabad

Language Model Self-AssessmentMetacognition in Language ModelsLLM Self-CorrectionLLM ReliabilityAdaptive Computation
AskPDF
Feb 21, 2026

Spilled Energy in Large Language Models

We reinterpret the final Large Language Model (LLM) softmax classifier as an Energy-Based Model (EBM), decomposing the sequence-to-sequence probability chain into multiple interacting EBMs at inference. This principled approach allows us to track "energy spills" during decoding, which we empirically show correlate with factual errors, biases, and failures. Similar to Orgad et al. (2025), our method localizes the exact answer token and subsequently tests for hallucinations. Crucially, however, we achieve this without requiring trained probe classifiers or activation ablations. Instead, we introduce two completely training-free metrics derived directly from output logits: spilled energy, which captures the discrepancy between energy values across consecutive generation steps that should theoretically match, and marginalized energy, which is measurable at a single step. Evaluated on nine benchmarks across state-of-the-art LLMs (including LLaMA, Mistral, and Gemma) and on synthetic algebraic operations (Qwen3), our approach demonstrates robust, competitive hallucination detection and cross-task generalization. Notably, these results hold for both pretrained and instruction-tuned variants without introducing any training overhead. Code available at: github.com/OmnAI-Lab/spilled-energy

Adrian Robert Minut, Hazem Dewidar, Iacopo Masi

Sapienza University of Rome, Italy · OmnAI Lab GLADIA

LLM ReliabilityLLM Hallucination DetectionEnergy-Based Models
AskPDF
Feb 20, 2026

Thinking by Subtraction: Confidence-Driven Contrastive Decoding for LLM Reasoning

Recent work on test-time scaling for large language model (LLM) reasoning typically assumes that allocating more inference-time computation uniformly improves correctness. However, prior studies show that reasoning uncertainty is highly localized: a small subset of low-confidence tokens disproportionately contributes to reasoning errors and unnecessary output expansion. Motivated by this observation, we propose Thinking by Subtraction, a confidence-driven contrastive decoding approach that improves reasoning reliability through targeted token-level intervention. Our method, Confidence-Driven Contrastive Decoding, detects low-confidence tokens during decoding and intervenes selectively at these positions. It constructs a contrastive reference by replacing high-confidence tokens with minimal placeholders, and refines predictions by subtracting this reference distribution at low-confidence locations. Experiments show that CCD significantly improves accuracy across mathematical reasoning benchmarks while substantially reducing output length, with minimal KV-cache overhead. As a training-free method, CCD enhances reasoning reliability through targeted low-confidence intervention without computational redundancy. Our code will be made available at: https://github.com/bolo-web/CCD.

Lexiang Tang, Weihao Gao, Bingchen Zhao +4

Peking University, Beijing, China · University of Edinburgh, Edinburgh, UK.

Efficient Language Model ReasoningLLM ReliabilityContrastive DecodingNumerical Reasoning in Language Models
AskPDF
Feb 19, 2026

Understanding Unreliability of Steering Vectors in Language Models: Geometric Predictors and the Limits of Linear Approximations

Steering vectors are a lightweight method for controlling language model behavior by adding a learned bias to the activations at inference time. Although effective on average, steering effect sizes vary across samples and are unreliable for many target behaviors. In my thesis, I investigate why steering reliability differs across behaviors and how it is impacted by steering vector training data. First, I find that higher cosine similarity between training activation differences predicts more reliable steering. Second, I observe that behavior datasets where positive and negative activations are better separated along the steering direction are more reliably steerable. Finally, steering vectors trained on different prompt variations are directionally distinct, yet perform similarly well and exhibit correlated efficacy across datasets. My findings suggest that steering vectors are unreliable when the latent target behavior representation is not effectively approximated by the linear steering direction. Taken together, these insights offer a practical diagnostic for steering unreliability and motivate the development of more robust steering methods that explicitly account for non-linear latent behavior representations.

Joschka Braun

Eberhard Karls University of Tübingen Faculty of Science

Language Model SteeringActivation SteeringLLM ReliabilityRepresentation Geometry in Language Models
AskPDF
Feb 19, 2026

Ontology-Guided Neuro-Symbolic Inference: Grounding Language Models with Mathematical Domain Knowledge

Language models exhibit fundamental limitations -- hallucination, brittleness, and lack of formal grounding -- that are particularly problematic in high-stakes specialist fields requiring verifiable reasoning. I investigate whether formal domain ontologies can enhance language model reliability through retrieval-augmented generation. Using mathematics as proof of concept, I implement a neuro-symbolic pipeline leveraging the OpenMath ontology with hybrid retrieval and cross-encoder reranking to inject relevant definitions into model prompts. Evaluation on the MATH benchmark with three open-source models reveals that ontology-guided context improves performance when retrieval quality is high, but irrelevant context actively degrades it -- highlighting both the promise and challenges of neuro-symbolic approaches.

Marcelo Labre

Advanced Institute for Artificial Intelligence (AI2)

Retrieval-Augmented GenerationLLM GroundingKnowledge Augmentation for Language ModelsLLM ReliabilityNeuro-Symbolic ReasoningLLM Mathematical Reasoning
AskPDF
Feb 19, 2026

Fine-Grained Uncertainty Quantification for Long-Form Language Model Outputs: A Comparative Study

Uncertainty quantification has emerged as an effective approach to closed-book hallucination detection for LLMs, but existing methods are largely designed for short-form outputs and do not generalize well to long-form generation. We introduce a taxonomy for fine-grained uncertainty quantification in long-form LLM outputs that distinguishes methods by design choices at three stages: response decomposition, unit-level scoring, and response-level aggregation. We formalize several families of consistency-based black-box scorers, providing generalizations and extensions of existing methods. We also introduce FactScore-STEM-Geo, a new 400-question long-form QA dataset spanning four categories across STEM and Geography. In our experiments across multiple LLMs and datasets, we find 1) claim-response entailment consistently performs better or on par with more complex claim-level scorers, 2) claim-level scoring generally yields better results than sentence-level scoring, and 3) uncertainty-aware decoding is highly effective for improving the factuality of long-form outputs. Our framework clarifies relationships between prior methods, enables apples-to-apples comparisons, and provides practical guidance for selecting components for fine-grained UQ.

Dylan Bouchard, Mohit Singh Chauhan, Viren Bajaj +1

CVS Health, Wellesley, MA

LLM Hallucination MitigationHallucination in Language ModelsFactual Consistency EvaluationLLM ReliabilityLLM Hallucination DetectionLLM Uncertainty Estimation
AskPDF
Feb 19, 2026

The Emergence of Lab-Driven Alignment Signatures: A Psychometric Framework for Auditing Latent Bias and Compounding Risk in Generative AI

Large language models increasingly serve as reasoning layers in multi-agent systems, where one provider's models may generate, judge, and summarize within a single pipeline. This raises the question of whether developer organizations impart durable behavioral tendencies that could compound across such stacks. We apply a scenario-based forced-choice instrument to 18 governance-relevant behavioral dimensions across 18 models from six developer organizations. Items are model-generated, filtered by independent judges, and administered with probe blanks embedded among semantically orthogonal decoys under deterministic option shuffling. Findings are declared on effect size, requiring both Holm-corrected significance and |d| >= 0.2. Across the 14 dimensions on which one scale pole denotes a defined response failure -- sycophancy, false balance, overconfidence, and others -- organizations occupy consistent relative positions (Kendall's W = 0.527, p = 6e-6), with Anthropic ranking first or second on 13 of 14 and Meta fifth on 10 of 14. On dimensions measuring directional valence without a normatively correct pole, no such concordance appears (W = 0.289, p = 0.48): organizations differ reliably in resistance to defined failures, not in ideological lean. Model-level variation within an organization is comparable in magnitude to variation between organizations, and is reported in full. Secondarily, across four major-version transitions, later generations scored lower on deficiency-poled dimensions in 26 of 30 comparisons. All 18 dimensions are reported, including three showing no organization-level differences, and a controlled test of the decoy manipulation returns a null result.

Dusan Bosnjakovic

Language Model AuditingLanguage Model Bias EvaluationLLM ReliabilityLLM Sycophancy
AskPDF
Feb 18, 2026

Are LLMs Ready to Replace Bangla Annotators?

Large Language Models (LLMs) are increasingly used as automated annotators to scale dataset creation, yet their reliability as unbiased annotators--especially for low-resource and identity-sensitive settings--remains poorly understood. In this work, we study the behavior of LLMs as zero-shot annotators for Bangla hate speech, a task where even human agreement is challenging, and annotator bias can have serious downstream consequences. We conduct a systematic benchmark of 17 LLMs using a unified evaluation framework. Our analysis uncovers annotator bias and substantial instability in model judgments. Surprisingly, increased model scale does not guarantee improved annotation quality--smaller, more task-aligned models frequently exhibit more consistent behavior than their larger counterparts. These results highlight important limitations of current LLMs for sensitive annotation tasks in low-resource languages and underscore the need for careful evaluation before deployment.

Md. Najib Hasan, Touseef Hasan, Souvika Sarkar

A2I Lab, School of Computing, Wichita State University

LLM-Assisted AnnotationLLM ReliabilityLanguage Model Bias EvaluationHate Speech Detection
AskPDF
Feb 18, 2026

Know When You're Wrong: Aligning Confidence with Correctness for LLM Error Detection

As large language models (LLMs) are increasingly deployed in critical decision-making systems, the lack of reliable methods to measure their uncertainty presents a fundamental trustworthiness risk. We introduce a normalized confidence score based on output anchor token probabilities: classification labels for structured tasks and self-evaluation responses (Yes/No) for open-ended generation. This enables direct detection of errors and hallucinations with minimal overhead and without external validation. We make three key contributions. First, we propose a normalized confidence score and self-evaluation framework that exposes reliable confidence estimates for error detection across seven diverse benchmark tasks and five LLMs of varying architectures and sizes. Second, our theoretical analysis reveals that supervised fine-tuning (SFT) yields well-calibrated confidence through maximum-likelihood estimation, whereas reinforcement learning methods (PPO, GRPO) and DPO induce overconfidence via reward exploitation. Third, we propose post-RL SFT with self-distillation to restore confidence reliability in RL-trained models. Empirical results demonstrated that SFT improved average confidence-correctness AUROC from 0.806 to 0.879 and reduced calibration error from 0.163 to 0.034 on Qwen3-4B, while GRPO and DPO degraded confidence reliability. We demonstrated practical value through adaptive retrieval-augmented generation (RAG) that selectively retrieves context when the model lacks confidence, using only 58% of retrieval operations to recover 95% of the maximum achievable accuracy gain on TriviaQA

Xie Xiaohu, Liu Xiaohu, Yao Benjamin

Alexa AI, Amazon, Seattle, WA, USA

Language Model Error DetectionConfidence Estimation in Language ModelsLLM ReliabilityLanguage Model Calibration
AskPDF
Feb 17, 2026

Gemma Needs Help: Investigating and Mitigating Emotional Instability in LLMs

Large language models can generate responses that resemble emotional distress, and this raises concerns around model reliability and safety. We introduce a set of evaluations to investigate expressions of distress in LLMs, and find that these surface emotional instability in Gemma and Gemini models, but not in other families. We find evidence that this difference arises in post-training. Base models from different families (Gemma, Qwen and OLMo) show similar propensities for expressing distress. However, instruct-tuned Gemma expresses substantially more distress than its base model, whereas instruct-tuned Qwen and OLMo express less. We find a simple mitigation for this: direct preference optimisation on just 280 preference pairs reduces Gemma's high-frustration responses from 35% to 0.3% in our evaluations, generalising across question types, user tones, and conversation lengths, without affecting capabilities. These findings show that emotional instability is an issue in some LLMs. We present (1) evaluations to track this behaviour, and (2) a mitigation without downsides in Gemma, with the caveat that upstream training modifications to improve emotional robustness would be significantly better than this post-hoc fix.

Anna Soligo, Vladimir Mikulik, William Saunders

Imperial College London · Anthropic Fellows · Anthropic

Language Model Safety EvaluationLLM Reliability
AskPDF
Feb 17, 2026

ReLoop: Structured Modeling and Behavioral Verification for Reliable LLM-Based Optimization

Large language models (LLMs) can translate natural-language problem descriptions into optimization code, but the code is prone to silent failures: it executes and returns a solver-feasible solution while encoding a semantically incorrect formulation. On compositional problems, the resulting feasibility-correctness gap reaches 90 percentage points. We introduce ReLoop, which combines two mechanisms. Structured generation decomposes code production into a four-stage reasoning chain (understand, formalize, synthesize, verify) to reduce formulation errors during generation. Behavioral verification detects the errors that remain by testing whether the formulation responds correctly to solver-based parameter perturbation, a signal that comes from the solver rather than from LLM self-review and requires no ground truth. The two mechanisms address different error structures: structured generation gives the largest gain on compositional problems (+8.5pp accuracy on RetailOpt-190 with Claude Opus 4.6), and behavioral verification gives its largest gain on localized defects (+4.4pp on MAMO-ComplexLP). With diagnostic execution recovery, ReLoop reaches 100% executable code on Claude Opus 4.6, and relative to direct generation it raises or preserves every reported metric of the three chat-tuned foundation models on all three benchmarks. For the narrowly fine-tuned SFT model we test, the chain-of-thought prompt conflicts with its learned output format and lowers its accuracy on MAMO-ComplexLP; we document and analyze this interaction. We release RetailOpt-190, 190 compositional retail optimization scenarios in which several constraints interact.

Junbo Jacob Lian, Yujun Sun, Huiling Chen +3

Institute of Operations Research and Analytics, National University of Singapore · McCormick School of Engineering, Northwestern University · Wenzhou Buyi Pharmacy Chain Co., Ltd. +2

LLM-Based Program SynthesisLLM ReliabilityNatural Language to Optimization Modeling
AskPDF
Feb 17, 2026

Improving LLM Reliability through Hybrid Abstention and Adaptive Detection

Large Language Models (LLMs) deployed in production environments face a fundamental safety-utility trade-off either a strict filtering mechanisms prevent harmful outputs but often block benign queries or a relaxed controls risk unsafe content generation. Conventional guardrails based on static rules or fixed confidence thresholds are typically context-insensitive and computationally expensive, resulting in high latency and degraded user experience. To address these limitations, we introduce an adaptive abstention system that dynamically adjusts safety thresholds based on real-time contextual signals such as domain and user history. The proposed framework integrates a multi-dimensional detection architecture composed of five parallel detectors, combined through a hierarchical cascade mechanism to optimize both speed and precision. The cascade design reduces unnecessary computation by progressively filtering queries, achieving substantial latency improvements compared to non-cascaded models and external guardrail systems. Extensive evaluation on mixed and domain-specific workloads demonstrates significant reductions in false positives, particularly in sensitive domains such as medical advice and creative writing. The system maintains high safety precision and near-perfect recall under strict operating modes. Overall, our context-aware abstention framework effectively balances safety and utility while preserving performance, offering a scalable solution for reliable LLM deployment.

Ankit Sharma, Nachiket Tapas, Jyotiprakash Patra

Department of Computer Science & Engineering, Chhattisgarh Swami Vivekanand Technical University, Bhilai, Chhattisgarh, India

LLM GuardrailsLLM ReliabilityLLM SafetyLLM Abstention
AskPDF
Feb 14, 2026

On Calibration of Large Language Models: From Response To Capability

Accurate confidence estimation is critical for reliable use of large language models (LLMs). Prior work on LLM calibration largely focuses on response-level confidence, which estimates the correctness of a single generated output. However, this formulation is misaligned with many practical settings where the central question is how likely a model is to solve a query overall. We show that this mismatch results from the stochastic nature of modern LLM decoding, under which single-response correctness fails to reflect underlying model capability. To address this issue, we introduce capability calibration, a new evaluation framework for measuring how well query-level confidence aligns with a model's expected accuracy on individual queries. We formally distinguish capability calibration (CC) from response calibration (RC) and show that the two differ both theoretically and empirically. We further show that CC is better suited than RC to applications like pass@k prediction and inference budget allocation. Finally, we evaluate common confidence estimation methods to understand the practical feasibility of CC.

Sin-Han Yang, Cheng-Kuang Wu, Chieh-Yen Lin +3

Appier AI Research · National Taiwan University

LLM EvaluationConfidence Estimation in Language ModelsLanguage Model CalibrationLLM ReliabilityLLM Uncertainty EstimationConfidence Estimation
AskPDF
Feb 13, 2026

The System Hallucination Scale (SHS): A Human-Centered Instrument for Assessing Perceived Reliability of Large Language Models

Large language models routinely produce factually incorrect or misleading outputs, yet conventional automated benchmarks overlook how users perceive reliability during interaction. We introduce the System Hallucination Scale (SHS), a lightweight instrument modeling the famous System Usability Scale (SUS) and System Causability Scales (SCS). SHS measures perceived reliability across five dimensions: factual accuracy, source reliability, logical coherence, deceptiveness of presentation, and responsiveness to user guidance, using ten balanced Likert-scale items that provide a directional score and consistency diagnostic. In a supervised validation study with 193 participants (386 evaluations across 47 trained experimenters), SHS demonstrated strong internal consistency and high clarity, completing in an average of 4.2 minutes. Participants rated source verifiability and presentation deceptiveness worse than factual accuracy, indicating perceived vulnerabilities lie primarily in traceability and framing. As a proof of concept, SHS assesses human-perceived reliability rather than ground-truth correctness, providing open-source multilingual implementations and an interactive calculator.

Heimo Müller, Dominik Steiger, Markus Plass +1

Machine Learning and Information Science Group, Medical University of Graz, Austria · Human Machine Mind Cooperation, Graz, Austria · MIDATA Cooperative, Zurich, Switzerland +1

LLM EvaluationLLM ReliabilityHallucination in Language Models
AskPDF
Feb 12, 2026

Are Two LLMs Better Than One? A Student-Teacher Dual-Head LLMs Architecture for Pharmaceutical Content Optimization

Large Language Models (LLMs) are increasingly used for content creation in regulated domains such as pharmaceuticals, where content must be medical accurate and legally compliant. Traditional manual quality control (QC) is slow, error-prone, and create publication bottlenecks. To address this, we introduce a modular, LLM/VLMs-driven QC architecture, LRBTC (Language, Regulatory, Brand, Technical, Content Structure), implemented through a Student Teacher HITL architecture and Waterfall rule filtering logic for scalable, verifiable content validation. This architecture is designed to provide verifiable, traceable, and scalable content optimization. Our methods achieve 83.0% F1 and 97.5% recall on AIReg Bench, reducing missed violations five fold compared with Gemini 2.5 Pro. On CSpelling, it improves mean accuracy by +26.7 %. Our error analysis further reveals that while current models are strong at detecting misspellings (92.5% recall), they fail to identify complex grammatical (25.0% recall) and punctuation (41.7% recall) errors, highlighting a key area for future work. This work provides a practical, plug-and-play solution for reliable, transparent quality control of content in high-stakes, compliance-critical industries. We also provide demo access.

Suyash Mishra, Qiang Li, Anubhav Girdhar

Roche · Accenture · Involead

AI Regulatory ComplianceLLM ReliabilityLanguage Model Error Detection
AskPDF
Feb 12, 2026

When Agents Disagree With Themselves: Behavioral Consistency as an Uncertainty Signal for LLM Agents

Running the same LLM agent on identical inputs yields 2.3-4.2 distinct action sequences per 10 runs; this behavioral variance constitutes a training-free, black-box uncertainty signal that instantiates selective classification and distribution-free calibration for agentic systems. Across 8,000 runs of four models on 200 HotpotQA questions, consistent tasks (at most 2 unique paths) achieve 82-87% accuracy while inconsistent tasks (4 or more paths) achieve 41-65%, a gap that survives controls for task difficulty. Divergence concentrates at step 2 (50.5% of Llama tasks), and consistency metrics detect failures with AUROC 0.62-0.78. Exploiting this signal, selective prediction (answering only when k=3 runs agree) achieves 87-88% accuracy at 54-62% coverage, a 6-14pp gain over single-run baselines, and matches a split-conformal baseline without a held-out calibration set. A cross-benchmark validation on SWE-bench (50 tasks, 1,000 runs) preserves the consistency hierarchy while revealing an ~8x spread in mean trajectory length across models, and bootstrap analysis shows single-run evaluations misrank models 29.3% of the time.

Aman Mehta

Snowflake AI Research

AI Agent ReliabilitySelective PredictionLLM Agent EvaluationReasoning Consistency in Language ModelsLanguage Model CalibrationLLM Reliability+3
AskPDF
Feb 4, 2026

Decomposed Prompting Does Not Fix Knowledge Gaps, But Helps Models Say "I Don't Know"

Large language models often struggle to recognize their knowledge limits in closed-book question answering, leading to confident hallucinations. While decomposed prompting is typically used to improve accuracy, we investigate its impact on reliability. We evaluate three task-equivalent prompting regimes: Direct, Assistive, and Incremental, across different model scales and multi-hop QA benchmarks. We find that although accuracy gains from decomposition diminish in frontier models, disagreements between prompting regimes remain highly indicative of potential errors. Because factual knowledge is typically stable while hallucinations are stochastic, cross-regime agreement provides a precise signal of internal uncertainty. We leverage this signal to implement a training-free abstention policy that requires no retrieval or fine-tuning. Our results show that disagreement-based abstention outperforms standard uncertainty baselines as an error detector, improving both F1 and AUROC across settings. This demonstrates that decomposition-based prompting can serve as a practical diagnostic probe for model reliability in closed-book QA.

Dhruv Madhwal, Lyuxin David Zhang, Dan Roth +2

Arizona State University · University of Pennsylvania · Oracle AI

LLM PromptingQuestion DecompositionLLM ReliabilityLLM Hallucination DetectionLLM Uncertainty EstimationLLM Abstention
AskPDF
Feb 4, 2026

Semantic Self-Distillation for Language Model Uncertainty

Large language models present challenges for principled uncertainty quantification, in part due to their complexity and the diversity of their outputs. Semantic dispersion, or the variance in the meaning of sampled answers, has been proposed as a useful proxy for model uncertainty, but the associated computational cost prohibits its use in latency-critical applications. We show that sampled semantic distributions can be distilled into lightweight student models which estimate a prompt-conditioned density before the language model generates an answer token. The student model predicts a semantic distribution over possible answers; the entropy of this distribution provides a prompt-level uncertainty signal, and the probability density allows answer-level reliability evaluation. Across experiments on TriviaQA and MMLU, we find our student models perform competitively relative to the teacher's sampled semantic dispersion on a hallucination prediction task, whilst offering additional uncertainty primitives for out-of-domain detection and multiple-choice answer selection. We term this technique Semantic Self-Distillation (SSD), which can serve as a general framework for distilling predictive uncertainty in complex output spaces beyond language.

Edward Phillips, Sean Wu, Fredrik K. Gustafsson +2

Department of Engineering Science, University of Oxford · Oxford Suzhou Centre for Advanced Research, University of Oxford, Suzhou

Uncertainty QuantificationConfidence Estimation in Language ModelsLLM ReliabilityLanguage Model DistillationLLM Uncertainty EstimationSemantic Uncertainty Estimation
AskPDF
Feb 2, 2026

HALT: Hallucination Assessment via Log-probs as Time series

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.

Ahmad Shapiro, Karan Taneja, Ashok Goel

Georgia Institute of Technology · Microsoft

Language Model Error DetectionHallucination DetectionHallucination in Language ModelsLLM ReliabilityLLM Hallucination Detection
AskPDF
Feb 2, 2026

Uncertainty Localization in LLM Reasoning via Embedding Perturbations

Large Language Models (LLMs) have achieved significant breakthroughs across various domains, but they can still produce unreliable or misleading outputs. For responsible LLM applications, uncertainty quantification techniques are used to estimate a model's uncertainty about its outputs, indicating the likelihood that those outputs may be problematic. For LLM reasoning tasks, it is essential to estimate uncertainty not only in the final answer but also in the intermediate reasoning process, particularly to identify where uncertainty arises. Such information may enable more fine-grained and targeted interventions during inference. In this study, we investigate which metrics can effectively localize uncertain places within an LLM reasoning trajectory. Our study reveals that uncertain intermediate continuations are more likely to occur at tokens that are highly sensitive to perturbations in the embeddings of preceding tokens. In our experiments, we show that such perturbation-based metrics achieve stronger performance in localizing uncertain intermediate steps than baseline methods, including probability-based, sampling-based, and Bayesian-based approaches. Meanwhile, our proposed metrics also enjoy good simplicity and efficiency.

Qihao Wen, Jiahao Wang, Yang Nan +3

University of Arizona · Michigan State University

LLM ReliabilityLLM Uncertainty EstimationLLM Reasoning
AskPDF
Jan 29, 2026

MGSM-Pro: A Simple Strategy for Robust Multilingual Mathematical Reasoning Evaluation

Large language models have made substantial progress in mathematical reasoning. However, benchmark development for multilingual evaluation has lagged behind English in both difficulty and recency. Recently, GSM-Symbolic showed a strong evidence of high variance when models are evaluated on different instantiations of the same question; however, the evaluation was conducted only in English. In this paper, we introduce MGSM-Pro, an extension of MGSM dataset with GSM-Symbolic approach. Our dataset provides five instantiations per MGSM question by varying names, digits and irrelevant context. Evaluations across nine languages reveal that many low-resource languages suffer large performance drops when tested on digit instantiations different from those in the original test set. We further find that models robustness in HRL setting do not necessarily translate to LRL. Moreover, proprietary models, such as Gemini 2.5 Flash and GPT-4.1 are less robust to digit, whereas Gemini 3.0 Pro is more robust. Among open models, GPT-OSS 120B and DeepSeek v3 show stronger robustness. Based on these findings, we recommend evaluating each problem using at least five digit-varying instantiations to obtain a more robust and realistic assessment of math reasoning.

Tianyi Xu, Kosei Uemura, Alfred Malengo Kondoro +6

McGill University · Mila-Quebec AI Institute · University of Toronto +7

Numerical Reasoning in Language ModelsMathematical Reasoning BenchmarksMultilingual Language Model EvaluationLLM ReliabilityLanguage Model RobustnessLLM Mathematical Reasoning
AskPDF
Jan 28, 2026

Bayesian-LoRA: Probabilistic Low-Rank Adaptation of Large Language Models

Large Language Models usually put more emphasis on accuracy and therefore, will guess even when not certain about the prediction, which is especially severe when fine-tuned on small datasets due to the inherent tendency toward miscalibration. In this work, we introduce Bayesian-LoRA, which reformulates the deterministic LoRA update as a probabilistic low-rank representation inspired by Sparse Gaussian Processes. We identify a structural isomorphism between LoRA's factorization and Kronecker-factored SGP posteriors, and show that LoRA emerges as a limiting case when posterior uncertainty collapses. We conduct extensive experiments on various LLM architectures across commonsense reasoning benchmarks. With only approximately 0.42M additional parameters and ≈1.2×{\approx}1.2{\times} training cost relative to standard LoRA, Bayesian-LoRA significantly improves calibration across models up to 30B, achieving up to 84% ECE reduction and 76% NLL reduction while maintaining competitive accuracy for both in-distribution and out-of-distribution (OoD) evaluations.

Moule Lin, Shuhao Guan, Andrea Patane +2

School of Computer Science and Statistics, Trinity College Dublin, Dublin, Ireland and Lero the Research Ireland Centre for Software, Ireland · School of Computer Science, University College Dublin, Dublin, Ireland

Bayesian Neural NetworksConfidence Estimation in Language ModelsLLM Fine-TuningLow-Rank AdaptationLanguage Model CalibrationLLM Reliability+2
AskPDF
Jan 21, 2026

AdversaRiskQA: An Adversarial Factuality Benchmark for High-Risk Domains

Hallucination in large language models (LLMs) remains an acute concern, contributing to the spread of misinformation and diminished public trust, particularly in high-risk domains. Among hallucination types, factuality is crucial, as it concerns a model's alignment with established world knowledge. Adversarial factuality, defined as the deliberate insertion of misinformation into prompts with varying levels of expressed confidence, tests a model's ability to detect and resist confidently framed falsehoods. Existing work lacks high-quality, domain-specific resources for assessing model robustness under such adversarial conditions, and no prior research has examined the impact of injected misinformation on long-form text factuality. To address this gap, we introduce AdversaRiskQA, the first verified and reliable benchmark systematically evaluating adversarial factuality across Health, Finance, and Law. The benchmark includes two difficulty levels to test LLMs' defensive capabilities across varying knowledge depths. We propose two automated methods for evaluating the adversarial attack success and long-form factuality. We evaluate six open- and closed-source LLMs from the Qwen, GPT-OSS, and GPT families, measuring misinformation detection rates. Long-form factuality is assessed on Qwen3 (30B) under both baseline and adversarial conditions. Results show that after excluding meaningless responses, Qwen3 (80B) achieves the highest average accuracy, while GPT-5 maintains consistently high accuracy. Performance scales non-linearly with model size, varies by domains, and gaps between difficulty levels narrow as models grow. Long-form evaluation reveals no significant correlation between injected misinformation and the model's factual output. AdversaRiskQA provides a valuable benchmark for pinpointing LLM weaknesses and developing more reliable models for high-stakes applications.

Adam Szelestey, Sofie van Engelen, Tianhao Huang +3

Eindhoven University of Technology Eindhoven, Netherlands

Factual Consistency EvaluationLLM ReliabilityAdversarial Robustness of Language Models
AskPDF
Jan 20, 2026

Vulnerability of LLMs' Stated Beliefs? LLMs Belief Resistance Check Through Strategic Persuasive Conversation Interventions

Large Language Models (LLMs) are increasingly employed in various question-answering tasks. However, recent studies showcase that LLMs are susceptible to persuasion and could adopt counterfactual beliefs. We present a systematic evaluation of LLM susceptibility to persuasion under the Source--Message--Channel--Receiver (SMCR) communication framework. Across six mainstream Large Language Models (LLMs) and three domains (factual knowledge, medical QA, and social bias), we analyze how different persuasive strategies influence stated belief stability over multiple interaction turns. We further examine whether verbalized confidence prompting (i.e., eliciting self-reported confidence scores) affects resistance to persuasion. Results show that the smallest model (Llama 3.2-3B) exhibits extreme compliance, with 82.5% of belief changes occurring at the first persuasive turn (average end turn of 1.1--1.4). Contrary to expectations, verbalized confidence prompting increases vulnerability by accelerating belief erosion rather than enhancing robustness. Finally, an exploratory study of adversarial fine-tuning reveals highly model-dependent effectiveness: GPT-4o-mini achieves near-complete robustness (98.6%), and Mistral~7B improves substantially (35.7% →\rightarrow 79.3%), but Llama models remain highly susceptible (<<14% RQ1) even when fine-tuned on their own failure cases. Together, these findings highlight substantial model-dependent limits of current robustness interventions and offer guidance for developing more trustworthy LLMs.

Fan Huang, Haewoon Kwak, Jisun An

Indiana University Bloomington, United States

LLM EvaluationFine-TuningLLM ReliabilityBelief Updating in LLMsPersuasion in Language ModelsLanguage Model Robustness
AskPDF
Jan 16, 2026

Relational Linearity is a Predictor of Hallucinations

Hallucination is a central failure mode of language models (LMs). We focus on hallucinations in response to questions like: "Which instrument did Glenn Gould play?", but we ask these questions for synthetic entities designed to be unknown to the model. We find that LMs like Gemma-7B-IT frequently hallucinate, i.e., they have difficulty recognizing that the hallucinated fact is not part of their knowledge. Based on the idea of linear relational embeddings, we put forward the following hypothesis. (i) Due to the abstract scheme that is used to represent them, LMs can easily produce plausible objects for non-existing subjects of linear relations, which can lead to hallucinations. (ii) For nonlinear relations, this mechanism for producing an object is not available and so a hallucination is easier to avoid. To test this hypothesis, we create SynthHal, a synthetic unknown-entity benchmark for 15 relations. We find that across four instruction-tuned models, relational linearity is a strong predictor of models hallucinating an object for an unknown subject vs refusing to give an answer, with correlations r∈[.58,.84]r \in [.58, .84]. While this is not direct evidence for the hypothesized causal mechanism, it is suggestive and opens up a new line of inquiry into understanding LM hallucinations.

Yuetian Lu, Yihong Liu, Sebastian Gerstner +3

Center for Information and Language Processing (CIS), LMU Munich · Ubiquitous Knowledge Processing Lab (UKP Lab), Technical University of Darmstadt · Munich Center for Machine Learning (MCML)

LLM InterpretabilityHallucination in Language ModelsLLM ReliabilityFactual Knowledge in Language Models
AskPDF
Jan 16, 2026

NOVA: NOise-aware Verbal Confidence CAlibration for Robust Large Language Models in RAG Systems

Accurately assessing model confidence is essential for deploying large language models (LLMs) in mission-critical factual domains. While retrieval-augmented generation (RAG) is widely adopted to improve grounding, confidence calibration in RAG settings remains poorly understood. We conduct a systematic study across four benchmarks, revealing that LLMs exhibit poor calibration performance especially when noisy contexts are retrieved. Specifically, contradictory or irrelevant evidence tends to exacerbate the model's overconfidence issue. To address this, we propose NOVA Rules (NOise-Aware Verbal Confidence CAlibration Rules) to provide a principled foundation for resolving overconfidence under noise. We further design NOVA, a noise-aware calibration framework that synthesizes supervision from ~2K HotpotQA examples guided by these rules. By performing supervised fine-tuning (SFT) with this data, NOVA equips models with intrinsic noise awareness without relying on stronger teacher models. Empirical results show that NOVA yields substantial gains, improving ECE scores by 10.9% in-domain and 8.0% out-of-domain. By bridging the gap between retrieval noise and verbal calibration, NOVA paves the way for both accurate and epistemically reliable LLMs.

Jiayu Liu, Rui Wang, Qing Zong +9

HKUST · UIUC · Northwestern University

Retrieval-Augmented GenerationConfidence Estimation in Language ModelsLanguage Model CalibrationLLM ReliabilityLanguage Model Robustness
AskPDF
Jan 12, 2026

Calibration Is Not Enough: Evaluating Confidence Estimation Under Language Variations

Confidence estimation (CE) indicates how reliable the answers of large language models are and impacts user trust and decision-making. Existing evaluations mainly concern the alignment between confidence and correctness, but ignore the variability of language: confidence estimates should remain consistent under semantically equivalent prompts or answer variations, while changing when answer meaning differs, as this may indicate a change in correctness. Therefore, we introduce a novel evaluation framework based on three complementary properties: robustness to prompt perturbations, stability across semantically equivalent answers, and sensitivity to semantically different answers. We show that these metrics are largely independent from existing CE metrics, and that common CE methods often fail on them: while most methods achieve high robustness and stability, they struggle to distinguish semantically different answers, potentially because they do not effectively leverage generation-side information. Overall, our framework exposes overlooked limitations of current CE evaluations and provides guidance for selecting confidence estimators for real-world applications.

Yuxi Xia, Dennis Ulmer, Terra Blevins +3

Faculty of Computer Science, UniVie Doctoral School Computer Science · Faculty of Philological and Cultural Studies, University of Vienna, Austria · ILLC, University of Amsterdam, Netherlands +2

LLM Uncertainty EstimationConfidence Estimation in Language ModelsLanguage Model Self-AssessmentLLM EvaluationLanguage Model CalibrationLLM Reliability+1
AskPDF
Jan 12, 2026

Stochastic CHAOS: Why Deterministic Inference Kills, and Distributional Variability Is the Heartbeat of Artifical Cognition

Deterministic inference is a comforting ideal in classical software: the same program on the same input should always produce the same output. As large language models move into real-world deployment, this ideal has been imported wholesale into inference stacks. Recent work from the Thinking Machines Lab has presented a detailed analysis of nondeterminism in LLM inference, showing how batch-invariant kernels and deterministic attention can enforce bitwise-identical outputs, positioning deterministic inference as a prerequisite for reproducibility and enterprise reliability. In this paper, we take the opposite stance. We argue that, for LLMs, deterministic inference kills. It kills the ability to model uncertainty, suppresses emergent abilities, collapses reasoning into a single brittle path, and weakens safety alignment by hiding tail risks. LLMs implement conditional distributions over outputs, not fixed functions. Collapsing these distributions to a single canonical completion may appear reassuring, but it systematically conceals properties central to artificial cognition. We instead advocate Stochastic CHAOS, treating distributional variability as a signal to be measured and controlled. Empirically, we show that deterministic inference is systematically misleading. Single-sample deterministic evaluation underestimates both capability and fragility, masking failure probability under paraphrases and noise. Phase-like transitions associated with emergent abilities disappear under greedy decoding. Multi-path reasoning degrades when forced onto deterministic backbones, reducing accuracy and diagnostic insight. Finally, deterministic evaluation underestimates safety risk by hiding rare but dangerous behaviors that appear only under multi-sample evaluation.

Tanmay Joshi, Shourya Aggarwal, Anusa Saha +7

Pragya Lab, BITS Pilani Goa, India · Raapid Lab, USA · Apple, USA +1

Emergent Abilities in Language ModelsLLM ReliabilityLLM Evaluation
AskPDF