Faithfulness of Language Model Reasoning

Latest papers

41 papers20 papers in the last four weeks, against 2 the four weeks before. 0.1% of all new papers.

Lost in Interpretation: The Plausibility-Faithfulness Trade-off in Cross-Lingual Explanations
May 19, 2026Somnath Banerjee, Pranav Jha, Rima Hazra +1Language Model Auditing Cross-Lingual Reasoning in Language Models
Indian Institute of Technology Kharagpur · TCG Crest · National University of Singapore
Drop the Act: Probe-Filtered RL for Faithful Chain-of-Thought Reasoning
May 12, 2026Swapnil Parekh, Naman GoyalRL for Language Model Reasoning Faithfulness of Language Model Explanations
Intuit
The Reasoning Trap: An Information-Theoretic Bound on Closed-System Multi-Step LLM Reasoning
May 3, 2026Kwan Soo ShinReasoning Evaluation Evidence-Grounded Reasoning
PolymathMinds AI Lab
RSAT: Structured Attribution Makes Small Language Models Faithful Table Reasoners
Apr 30, 2026Jugal Gajjar, Kamalasankari SubramaniakuppusamyLLM Reasoning LLM Grounding
Department of Computer Science, The George Washington University, USA
Verify Before You Commit: Towards Faithful Reasoning in LLM Agents via Self-Auditing
Apr 9, 2026Wenhao Yuan, Chenchen Lin, Jian Chen +3Faithfulness of Language Model Reasoning LLM Agent Reliability
The University of Hong Kong · Sun Yat-sen University
Measuring and curing reasoning rigidity: from decorative chain-of-thought to genuine faithfulness
Mar 24, 2026Abhinaba Basu, Pavan ChakrabortyLanguage Model Reasoning Evaluation Structured Reasoning in Language Models
Indian Institute of Information Technology Allahabad (IIITA) · National Institute of Electronics and Information Technology (NIELIT)
Lie to Me: How Faithful Is Chain-of-Thought Reasoning in Reasoning Models?
Mar 23, 2026Richard J. YoungCoT Faithfulness Faithfulness of Language Model Explanations
University of Nevada, Las Vegas, Department of Management, Entrepreneurship and Technology, Lee Business School, Las Vegas, NV, USA · DeepNeuro AI, Las Vegas, NV, USA
Reasoning Theater: Disentangling Model Beliefs from Chain-of-Thought
Mar 5, 2026Siddharth Boppana, Annabel Ma, Max Loeffler +5Faithfulness of Language Model Reasoning Language Model Reasoning Evaluation
Goodfire AI · Harvard University, Cambridge, MA
The Imperfective Paradox in Large Language Models
Jan 14, 2026Bolei Ma, Yusuke MiyaoFaithfulness of Language Model Reasoning Language Model Reasoning Evaluation
LMU Munich & MCML · The University of Tokyo
Do Latent Tokens Think? A Causal and Adversarial Analysis of Chain-of-Continuous-Thought
Dec 25, 2025Yuyi Zhang, Boyu Tang, Tianjie Ju +2Faithfulness of Language Model Reasoning Implicit Reasoning in Language Models
Shanghai Jiao Tong University
The Ends Justify the Thoughts: RL-Induced Motivated Reasoning Fools CoT Monitors
Oct 20, 2025Nikolaus Howe, Micah CarrollLLM Safety Monitoring CoT Monitoring
Mila, Université de Montréal · UC Berkeley

May 19, 2026J/K move · Enter open · S save

Lost in Interpretation: The Plausibility-Faithfulness Trade-off in Cross-Lingual Explanations

Somnath Banerjee, Pranav Jha, Rima Hazra, Animesh Mukherjee

Indian Institute of Technology Kharagpur · TCG Crest · National University of Singapore

Language Model Auditing Cross-Lingual Reasoning in Language Models LLM Interpretability Explainability Evaluation Multilingual Language Model Evaluation Faithfulness of Language Model Explanations+3

Open paper AskPDF arXiv

LLMs deployed multilingually are often audited via English explanations for non-English inputs. We evaluate extractive explanations ''where the model identifies input token spans as evidence alongside a generated rationale'' and uncover a systematic trade-off: English-pivot explanations can achieve higher span agreement with human rationales while their evidence becomes less causally grounded in the model's prediction, as measured by both comprehensiveness and sufficiency. Across 3 tasks, 5~~languages, and 2~~multilingual LLM families, we find that English explanations frequently produce fluent but loosely anchored rationales, with comprehensiveness degrading by up to 5.7x relative to native-language conditions - even as task accuracy remains stable across settings. For socially nuanced classification, English pivots also fail to preserve pragmatic cues, reducing both faithfulness and span agreement. We recommend auditing explanations in the input language, reporting multi-faceted faithfulness metrics beyond lexical overlap, and treating English rationales as communication summaries rather than faithful decision traces.