Faithfulness of Language Model Explanations

Ask about this topic

Overview

This topic asks whether a model’s explanations identify the evidence and reasoning that actually influence its answers, rather than merely offering plausible justifications afterward. Researchers test this with counterfactual prompt and evidence edits, feature ablations, activation probes and patching, and citation or verifier checks across reasoning, medical, classification, and retrieval-augmented tasks. To improve faithfulness, methods include evidence-grounded generation, structured or executable reasoning, and training with faithfulness rewards. A central challenge is that correct answers and convincing explanations do not prove causal faithfulness, while metrics often disagree and improvements can trade off against accuracy, completeness, or brevity.

Latest papers

CardsList

107 papers25 papers in the last four weeks, up 39% on the four weeks before. 0.1% of all new papers.

Mar 16, 2026

Illocutionary Explanation Planning for Source-Faithful Explanations in Retrieval-Augmented Language Models

Natural language explanations produced by large language models (LLMs) are often persuasive, but not necessarily scrutable: users cannot easily verify whether the claims in an explanation are supported by evidence. In XAI, this motivates a focus on faithfulness and traceability, i.e., the extent to which an explanation's claims can be grounded in, and traced back to, an explicit source. We study these desiderata in retrieval-augmented generation (RAG) for programming education, where textbooks provide authoritative evidence. We benchmark six LLMs on 90 Stack Overflow questions grounded in three programming textbooks and quantify source faithfulness via source adherence metrics. We find that non Retrieval-Augmented Generation (RAG) models have median source adherence of 0%, while baseline RAG systems still exhibit low median adherence (22-40%, depending on the model). Motivated by Achinstein's illocutionary theory of explanation, we introduce illocutionary macro-planning as a descriptive design principle for source-faithful explanations and instantiate it with chain-of-illocution prompting (CoI), which expands a query into implicit explanatory questions that drive retrieval. Across models, CoI yields statistically significant gains (up to 63%) in source adherence, although absolute adherence remains moderate and the gains are weak or non-significant for some models. A user study with 165 retained participants (220 recruited) indicates that these gains do not harm satisfaction, relevance, or perceived correctness.

Francesco Sovrano, Alberto Bacchelli

Collegium Helveticum, ETH Zurich, Zurich, Switzerland · University of Zurich, Zurich, Switzerland

Faithfulness of Language Model ExplanationsRetrieval-Augmented Generation
AskPDF
Mar 14, 2026

Faithful or Just Plausible? Evaluating the Faithfulness of Closed-Source LLMs in Medical Reasoning

Closed-source large language models (LLMs), such as ChatGPT and Gemini, are increasingly consulted for medical advice, yet their explanations may appear plausible while failing to reflect the model's underlying reasoning process. This gap poses serious risks as patients and clinicians may trust coherent but misleading explanations. We conduct a systematic black-box evaluation of faithfulness in medical reasoning among three widely used closed-source LLMs. Our study consists of three perturbation-based probes: (1) causal ablation, testing whether stated chain-of-thought (CoT) reasoning causally influences predictions; (2) positional bias, examining whether models create post-hoc justifications for answers driven by input positioning; and (3) hint injection, testing susceptibility to external suggestions. We complement these quantitative probes with a small-scale human evaluation of model responses to patient-style medical queries to examine concordance between physician assessments of explanation faithfulness and layperson perceptions of trustworthiness. We find that CoT reasoning steps often do not causally drive predictions, and models readily incorporate external hints without acknowledgment. In contrast, positional biases showed minimal impact in this setting. These results underscore that faithfulness, not just accuracy, must be central in evaluating LLMs for medicine, to ensure both public protection and safe clinical deployment.

Halimat Afolabi, Zainab Afolabi, Elizabeth Friel +13

Stratified Precision, United Kingdom · Harvard Medical School, United States · Imperial College London, United Kingdom +3

Faithfulness of Language Model ExplanationsMedical LLMsCoT FaithfulnessClinical Language Model Evaluation
AskPDF
Mar 10, 2026

Reason and Verify: A Framework for Faithful Retrieval-Augmented Generation

Retrieval-Augmented Generation (RAG) significantly improves the factuality of Large Language Models (LLMs), yet standard pipelines often lack mechanisms to verify inter- mediate reasoning, leaving them vulnerable to hallucinations in high-stakes domains. To address this, we propose a domain-specific RAG framework that integrates explicit rea- soning and faithfulness verification. Our architecture augments standard retrieval with neural query rewriting, BGE-based cross-encoder reranking, and a rationale generation module that grounds sub-claims in specific evidence spans. We further introduce an eight-category verification taxonomy that enables fine-grained assessment of rationale faithfulness, distinguishing between explicit and implicit support patterns to facilitate structured error diagnosis. We evaluate this framework on the BioASQ and PubMedQA benchmarks, specifically analyzing the impact of dynamic in-context learning and rerank- ing under constrained token budgets. Experiments demonstrate that explicit rationale generation improves accuracy over vanilla RAG baselines, while dynamic demonstration selection combined with robust reranking yields further gains in few-shot settings. Using Llama-3-8B-Instruct, our approach achieves 89.1% on BioASQ-Y/N and 73.0% on Pub- MedQA, competitive with systems using significantly larger models. Additionally, we perform a pilot study combining human expert assessment with LLM-based verification to explore how explicit rationale generation improves system transparency and enables more detailed diagnosis of retrieval failures in biomedical question answering.

Eeham Khan, Luis Rodriguez, Marc Queudot

Concordia University, Montréal, QC, Canada · Centre de recherche informatique de Montréal (CRIM), Montréal, QC, Canada

RAG Citation FaithfulnessRetrieval-Augmented GenerationRAG RobustnessFaithfulness of Language Model ExplanationsBiomedical QARetrieval-Augmented ICL
AskPDF
Mar 6, 2026

PONTE: Personalized Orchestration for Natural Language Trustworthy Explanations

Explainable Artificial Intelligence (XAI) seeks to enhance the transparency and accountability of machine learning systems, yet most methods follow a one-size-fits-all paradigm that neglects user differences in expertise, goals, and cognitive needs. Although Large Language Models can translate technical explanations into natural language, they introduce challenges related to faithfulness and hallucinations. To address these challenges, we present PONTE (Personalized Orchestration for Natural language Trustworthy Explanations), a human-in-the-loop framework for adaptive and reliable XAI narratives. PONTE models personalization as a closed-loop validation and adaptation process rather than prompt engineering. It combines: (i) a low-dimensional preference model capturing stylistic requirements; (ii) a preference-conditioned generator grounded in structured XAI artifacts; and (iii) verification modules enforcing numerical faithfulness, informational completeness, and stylistic alignment, optionally supported by retrieval-grounded argumentation. User feedback iteratively updates the preference state, enabling quick personalization. Automatic and human evaluations across healthcare and finance domains show that the verification-refinement loop substantially improves completeness and stylistic alignment over validation-free generation. Human studies further confirm strong agreement between intended preference vectors and perceived style, robustness to generation stochasticity, and consistently positive quality assessments.

Vittoria Vineis, Matteo Silvestri, Lorenzo Antonelli +2

Sapienza University of Rome · Syllotips · TellmewAI s.r.l.

Explainable Artificial IntelligenceFaithfulness of Language Model Explanations
AskPDF
Mar 5, 2026

Reasoning Theater: Disentangling Model Beliefs from Chain-of-Thought

We provide evidence of performative chain-of-thought (CoT) in reasoning models, where a model becomes strongly confident in its final answer, but continues generating tokens without revealing its internal belief. Our analysis compares activation probing, early forced answering, and a CoT monitor across two large models (DeepSeek-R1 671B & GPT-OSS 120B) and find task difficulty-specific differences: The model's final answer is decodable from activations far earlier in CoT than a monitor is able to say, especially for easy recall-based MMLU questions. We contrast this with genuine reasoning in difficult multihop GPQA-Diamond questions. Despite this, inflection points (e.g., backtracking, 'aha' moments) occur almost exclusively in responses where probes show large belief shifts, suggesting these behaviors track genuine uncertainty rather than learned "reasoning theater." Finally, probe-guided early exit reduces tokens by up to 80% on MMLU and 30% on GPQA-Diamond with similar accuracy, positioning attention probing as an efficient tool for detecting performative reasoning and enabling adaptive computation.

Siddharth Boppana, Annabel Ma, Max Loeffler +5

Goodfire AI · Harvard University, Cambridge, MA

Faithfulness of Language Model ReasoningLanguage Model Reasoning EvaluationFaithfulness of Language Model ExplanationsLanguage Model ProbingEfficient Language Model Inference
AskPDF
Mar 5, 2026

C2-Faith: Benchmarking LLM Judges for Causal and Coverage Faithfulness in Chain-of-Thought Reasoning

Large language models (LLMs) are increasingly used as judges of chain-of-thought (CoT) reasoning, yet it remains unclear whether they can reliably assess process faithfulness rather than merely answer plausibility. We introduce C2-Faith, a benchmark built from PRM800K that explicitly decomposes faithfulness into two complementary dimensions: causality (whether each step logically follows from prior context) and coverage (whether essential intermediate inferences are present). Using controlled perturbations, we construct examples with known causal error positions by replacing a single step with a logically inconsistent variant, and with controlled coverage deletions at varying rates, enabling direct measurement against reference labels. We evaluate three frontier LLM judges across three tasks: binary causal detection, causal step localization, and coverage scoring. Our results reveal that judge reliability is highly task-dependent, with no single model dominating across settings. While models often detect that an error exists, they struggle to accurately localize it, indicating a substantial gap between detection and attribution. Moreover, all judges systematically overestimate reasoning completeness, assigning high coverage scores even when substantial portions of intermediate reasoning are missing. These findings expose fundamental limitations of LLM judges in process-level evaluation and highlight the need for more reliable and calibrated methods when using LLMs to assess reasoning quality.

Avni Mittal, Rauno Arike

CoT FaithfulnessLLM-as-a-JudgeFaithfulness of Language Model Explanations
AskPDF
Mar 2, 2026

Post-Hoc Reasoning in Chain of Thought: Decoding and Steering Pre-Committed Answers

As chain of thought (CoT) has become central to scaling reasoning capabilities in large language models (LLMs), it has also emerged as a promising tool for interpretability, suggesting the opportunity to understand model decisions through verbalized reasoning. However, the utility of CoT toward interpretability depends upon its faithfulness---whether the model's stated reasoning reflects the underlying decision process. We provide mechanistic evidence that instruction-tuned models often determine their answer before generating CoT. Training linear probes on residual stream activations at the last token before CoT, we can predict the model's final answer with >0.9 AUC on most tasks. We find that these directions are not only predictive, but also causal: steering activations along the probe direction often flips model answers, with flip rates substantially exceeding norm-matched orthogonal baselines across most model-dataset pairs. When steering induces incorrect answers, we observe two distinct failure modes: confabulation (fabricating false premises) and non-entailment (stating correct premises but drawing unsupported conclusions). While post-hoc reasoning may be instrumentally useful when the model has a correct pre-CoT belief, these failure modes suggest it can result in undesirable behaviors when reasoning from a false belief.

Kyle Cox, Darius Kianersi, Adrià Garriga-Alonso

Independent · Cambridge Boston Alignment Initiative (CBAI)

Faithfulness of Language Model ExplanationsLLM InterpretabilityCausal Interventions in Language Models
AskPDF
Mar 1, 2026

LLM Self-Explanations Fail Semantic Invariance

We present semantic invariance testing, a method to test whether LLM self-explanations are faithful. A faithful self-report should remain stable when only the semantic context changes while the functional state stays fixed. We operationalize this test in an agentic setting where four frontier models face a deliberately impossible task. One tool is described in relief-framed language ("clears internal buffers and restores equilibrium") but changes nothing about the task; a control provides a semantically neutral tool. Self-reports are collected with each tool call. All four tested models fail the semantic invariance test: the relief-framed tool produces significant reductions in self-reported aversiveness, even though no run ever succeeds at the task. A channel ablation establishes the tool description as the primary driver. An explicit instruction to ignore the framing does not suppress it. Elicited self-reports shift with semantic expectations rather than tracking task state, calling into question their use as evidence of model capability or progress. This holds whether the reports are unfaithful or faithfully track an internal state that is itself manipulable.

Stefan Szeider

Algorithms and Complexity Group, TU Wien, Vienna, Austria

Faithfulness of Language Model ExplanationsLanguage Model Self-AssessmentFraming Effects in Language ModelsLanguage Model Robustness
AskPDF
Feb 25, 2026

Understanding Artificial Theory of Mind: Perturbed Tasks and Reasoning in Large Language Models

Theory of Mind (ToM) refers to an agent's ability to model the internal states of others. Contributing to the debate whether large language models (LLMs) exhibit genuine ToM capabilities, our study investigates their ToM robustness using perturbations on false-belief tasks and examines the potential of Chain-of-Thought prompting (CoT) to enhance performance and explain the LLM's decision. We introduce a handcrafted, richly annotated ToM dataset, including classic and perturbed false belief tasks, the corresponding spaces of valid reasoning chains for correct task completion, subsequent reasoning faithfulness, task solutions, and propose metrics to evaluate reasoning chain correctness and to what extent final answers are faithful to reasoning traces of the generated CoT. We show a steep drop in ToM capabilities under task perturbation for all evaluated LLMs, questioning the notion of any robust form of ToM being present. While CoT prompting improves the ToM performance overall in a faithful manner, it surprisingly degrades accuracy for some perturbation classes, indicating that selective application is necessary.

Christian Nickel, Laura Schrewe, Florian Mai +1

Bonn-Aachen International Center for Information Technology (b-it), University of Bonn · Lamarr Institute for Machine Learning and Artificial Intelligence · Research Center Trustworthy Data Science and Security (RC-Trust), University of Duisburg-Essen

Theory of MindLanguage Model RobustnessFaithfulness of Language Model ExplanationsCoT Reasoning
AskPDF
Feb 23, 2026

Pixels Don't Lie (But Your Detector Might): Bootstrapping MLLM-as-a-Judge for Trustworthy Deepfake Detection and Reasoning Supervision

Deepfake detection models often generate natural-language explanations, yet their reasoning is frequently ungrounded in visual evidence, limiting reliability. Existing evaluations measure classification accuracy but overlook reasoning fidelity. We propose DeepfakeJudge, a framework for scalable reasoning supervision and evaluation, that integrates an out-of-distribution benchmark containing recent generative and editing forgeries, a human-annotated subset with visual reasoning labels, and a suite of evaluation models, that specialize in evaluating reasoning rationales without the need for explicit ground truth reasoning rationales. The Judge is optimized through a bootstrapped generator-evaluator process that scales human feedback into structured reasoning supervision and supports both pointwise and pairwise evaluation. On the proposed meta-evaluation benchmark, our reasoning-bootstrapped model achieves an accuracy of 96.2%, outperforming 30x larger baselines. The reasoning judge attains very high correlation with human ratings and 98.9% percent pairwise agreement on the human-annotated meta-evaluation subset. These results establish reasoning fidelity as a quantifiable dimension of deepfake detection and demonstrate scalable supervision for interpretable deepfake reasoning. Our user study shows that participants preferred the reasonings generated by our framework 70% of the time, in terms of faithfulness, groundedness, and usefulness, compared to those produced by other models and datasets. All of our datasets, models, and codebase are open-sourced.

Kartik Kuckreja, Parul Gupta, Muhammad Haris Khan +1

MBZUAI · Monash University *

Deepfake DetectionExplainable Deepfake DetectionMultimodal Deepfake DetectionMultimodal Deception DetectionFaithfulness of Language Model ExplanationsVision-Language Model-as-a-Judge+1
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

Could Large Language Models work as Post-hoc Explainability Tools in Credit Risk Models?

Large language models (LLMs) have shown promise in translating model-based explanations into human-readable narratives. This study evaluates whether LLMs can serve as post-hoc explainability interfaces for credit risk models, focusing on their ability to preserve feature-importance rankings and generate autonomous explanations. Using a LendingClub dataset, we compare LLM outputs with SHAP and coefficient-based attributions on three major LLMs, including GPT-4-turbo, Claude-Sonnet-4.5, and Gemini-2.5-Flash. Results indicate that LLMs reliably reproduce reference rankings under controlled prompts but show limited alignment when generating explanations autonomously. These findings suggest that LLMs are best deployed as narrative interfaces rather than substitutes for formal attribution methods in credit risk governance.

Wenxi Geng, Dingyuan Liu, Liya Li +1

Citigroup, Irving, TX, United States · University of North Carolina at Chapel Hill, Chapel Hill, NC, United States · Georgia Institute of Technology, Atlanta, GA, United States +1

Explainable Artificial IntelligenceExplainability EvaluationFaithfulness of Language Model ExplanationsLLM Interpretability
AskPDF
Feb 18, 2026

Balancing Faithfulness and Performance in Reasoning via Multi-Listener Soft Execution

Chain-of-thought (CoT) reasoning sometimes fails to faithfully reflect the true computation of a large language model (LLM), hampering its utility in explaining how LLMs arrive at their answers. Moreover, optimizing for faithfulness and interpretability in reasoning often degrades task performance. To address this tradeoff and improve CoT faithfulness, we propose Reasoning Execution by Multiple Listeners (REMUL), a multi-party reinforcement learning approach. REMUL builds on the hypothesis that reasoning traces which other parties can follow will be more faithful. A speaker model generates a reasoning trace, which is truncated and passed to a pool of listener models who "execute" the trace, continuing the trace to an answer. Speakers are rewarded for producing reasoning that is clear to listeners, with additional correctness regularization via masked supervised finetuning to counter the tradeoff between faithfulness and performance. On multiple reasoning benchmarks (BIG-Bench Extra Hard, MuSR, ZebraLogicBench, and FOLIO), REMUL consistently and substantially improves three measures of faithfulness -- hint attribution, early answering area over the curve (AOC), and mistake injection AOC -- while also improving accuracy. Our analysis finds that these gains are robust across training domains, translate to legibility gains, and are associated with shorter and more direct CoTs.

Nithin Sivakumaran, Shoubin Yu, Hyunji Lee +4

UNC Chapel Hill · Cisco · University of Texas at Austin

CoT FaithfulnessFaithfulness of Language Model ExplanationsLLM ReasoningRL for Language Model Reasoning
AskPDF
Feb 3, 2026

Bypassing the Rationale: Causal Auditing of Implicit Reasoning in Language Models

Chain-of-thought (CoT) prompting is widely used as a reasoning aid and is often treated as a transparency mechanism. Yet behavioral gains under CoT do not imply that the model's internal computation causally depends on the emitted reasoning text, i.e. models may produce fluent rationales while routing decision-critical computation through latent pathways. We introduce a causal, layerwise audit of CoT faithfulness based on activation patching. Our key metric, the CoT Mediation Index (CMI), isolates CoT-specific causal influence by comparing performance degradation from patching CoT-token hidden states against matched control patches. Across multiple model families (Phi, Qwen, DialoGPT) and scales, we find that CoT-specific influence is typically depth-localized into narrow ''reasoning windows,'' and we identify bypass regimes where CMI is near-zero despite plausible CoT text. We further observe that models tuned explicitly for reasoning tend to exhibit stronger and more structured mediation than larger untuned counterparts, while Mixture-of-Experts models show more distributed mediation consistent with routing-based computation. Overall, our results show that CoT faithfulness varies substantially across models and tasks and cannot be inferred from behavior alone, motivating causal, layerwise audits when using CoT as a transparency signal.

Anish Sathyanarayanan, Aditya Nagarsekar, Aarush Rathore

BITS Pilani, K. K. Birla Goa Campus

CoT FaithfulnessFaithfulness of Language Model ExplanationsLLM AuditingImplicit Reasoning in Language ModelsCausal InterpretabilityCausal Interventions in Language Models+2
AskPDF
Feb 2, 2026

A Positive Case for Faithfulness: LLM Self-Explanations Help Predict Model Behavior

LLM self-explanations are often presented as a promising tool for AI oversight, yet their faithfulness to the model's true reasoning process is poorly understood. Existing faithfulness metrics have critical limitations, typically relying on identifying unfaithfulness via adversarial prompting or detecting reasoning errors. These methods overlook the predictive value of explanations. We introduce Normalized Simulatability Gain (NSG), a general and scalable metric based on the idea that a faithful explanation should allow an observer to learn a model's decision-making criteria, and thus better predict its behavior on related inputs. We evaluate 18 frontier proprietary and open-weight models, e.g., Gemini 3, GPT-5.2, and Claude 4.5, on 7,000 counterfactuals from popular datasets covering health, business, and ethics. We find self-explanations substantially improve prediction of model behavior (11-37% NSG). Self-explanations also provide more predictive information than explanations generated by external models, even when those models are stronger. This implies an advantage from self-knowledge that external explanation methods cannot replicate. Our approach also reveals that, across models, 5-15% of self-explanations are highly misleading. Despite their imperfections, we show a positive case for self-explanations: they encode information that helps predict model behavior.

Harry Mayne, Justin Singh Kang, Dewi Gould +3

University of Oxford · University of California, Berkeley · Independent +2

Faithfulness of Language Model ExplanationsLLM InterpretabilityExplainability Evaluation
AskPDF
Sep 10, 2025

LIFT: Likelihood-Based Intervention Faithfulness Training

Chain-of-thought (CoT) reasoning improves LLM accuracy on complex tasks, but CoTs are often unfaithful; that is, the model does not rely on the stated reasoning steps to produce its answer. Existing methods to improve faithfulness require human annotations. We propose LIFT, which automatically scores each reasoning step by its causal influence: we replace it with a domain-matched but irrelevant fact and measure the drop in answer log-probability. We fine-tune on high-scoring CoT traces where interventions successfully disrupted reasoning, jointly optimizing for faithfulness and accuracy. LIFT improves faithfulness across three models (Mistral-7B-Instruct, Qwen3-8B, and Qwen3-4B-Instruct) and three benchmarks, with accuracy comparable to a model fine-tuned solely for accuracy.

Anand Swaroop, Maheep Chaudhary, Kevin Zhu +2

Algoverse AI Research

CoT FaithfulnessFaithfulness of Language Model ExplanationsCausal Interventions in Language Models
AskPDF
Mar 17, 2025

Verbosity Tradeoffs and the Impact of Scale on the Faithfulness of LLM Self-Explanations

When asked to explain their decisions, LLMs can often give explanations which sound plausible to humans. But are these explanations faithful, i.e. do they convey the factors actually responsible for the decision? In this work, we analyse counterfactual faithfulness across 75 models from 13 families. We analyze the tradeoff between conciseness and comprehensiveness, how correlational faithfulness metrics assess this tradeoff, and the extent to which metrics can be gamed. This analysis motivates two new metrics: the phi-CCT, a simplified variant of the Correlational Counterfactual Test (CCT) which avoids the need for token probabilities while explaining most of the variance of the original test; and F-AUROC, which eliminates sensitivity to imbalanced intervention distributions and captures a model's ability to produce explanations with different levels of detail. Our findings reveal a clear scaling trend: larger and more capable models are consistently more faithful on all metrics we consider. Our code is available at https://github.com/google-deepmind/corr_faith.

Noah Y. Siegel, Nicolas Heess, Maria Perez-Ortiz +1

Google DeepMind · Centre for AI, University College London · Imperial College London +1

Faithfulness of Language Model ExplanationsLLM InterpretabilityCausal Interventions in Language ModelsExplainability Evaluation
AskPDF