Cover Image

Walk the Talk? Measuring the Faithfulness of Large Language Model Explanations

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Matton, Katie, Ness, Robert Osazuwa, Guttag, John, Kıcıman, Emre
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Causal Reasoning and Large Language Models: Opening a New Frontier for Causality
by: Kıcıman, Emre, et al.
Published: (2023)

FaithLM: Towards Faithful Explanations for Large Language Models
by: Chuang, Yu-Neng, et al.
Published: (2024)

Improving Domain Generalization in Contrastive Learning using Adaptive Temperature Control
by: Lewis, Robert, et al.
Published: (2026)

MedFuzz: Exploring the Robustness of Large Language Models in Medical Question Answering
by: Ness, Robert Osazuwa, et al.
Published: (2024)

Do Large Language Models Walk Their Talk? Measuring the Gap Between Implicit Associations, Self-Report, and Behavioral Altruism
by: Andric, Sandro
Published: (2025)

A Glitch in the Matrix? Locating and Detecting Language Model Grounding with Fakepedia
by: Monea, Giovanni, et al.
Published: (2023)

Still "Talking About Large Language Models": Some Clarifications
by: Shanahan, Murray
Published: (2024)

ContextFocus: Activation Steering for Contextual Faithfulness in Large Language Models
by: Anand, Nikhil, et al.
Published: (2026)

CELL your Model: Contrastive Explanations for Large Language Models
by: Luss, Ronny, et al.
Published: (2024)

Talking Nonsense: Probing Large Language Models' Understanding of Adversarial Gibberish Inputs
by: Cherepanova, Valeriia, et al.
Published: (2024)

Bridging the Bosphorus: Advancing Turkish Large Language Models through Strategies for Low-Resource Language Adaptation and Benchmarking
by: Acikgoz, Emre Can, et al.
Published: (2024)

On Measuring Faithfulness or Self-consistency of Natural Language Explanations
by: Parcalabescu, Letitia, et al.
Published: (2023)

Listen to the Context: Towards Faithful Large Language Models for Retrieval Augmented Generation on Climate Questions
by: Thulke, David, et al.
Published: (2025)

FaithEval: Can Your Language Model Stay Faithful to Context, Even If "The Moon is Made of Marshmallows"
by: Ming, Yifei, et al.
Published: (2024)

A Data-Centric Approach To Generate Faithful and High Quality Patient Summaries with Large Language Models
by: Hegselmann, Stefan, et al.
Published: (2024)

Direct Reasoning Optimization: Token-Level Reasoning Reflectivity Meets Rubric Gates for Unverifiable Tasks
by: Xu, Yifei, et al.
Published: (2025)

Measuring Chain-of-Thought Monitorability Through Faithfulness and Verbosity
by: Meek, Austin, et al.
Published: (2025)

LLMExplainer: Large Language Model based Bayesian Inference for Graph Explanation Generation
by: Zhang, Jiaxing, et al.
Published: (2024)

LLMCheckup: Conversational Examination of Large Language Models via Interpretability Tools and Self-Explanations
by: Wang, Qianli, et al.
Published: (2024)

Measuring Social Norms of Large Language Models
by: Yuan, Ye, et al.
Published: (2024)

Prompt-Response Semantic Divergence Metrics for Faithfulness Hallucination and Misalignment Detection in Large Language Models
by: Halperin, Igor
Published: (2025)

Can Large Language Models Still Explain Themselves? Investigating the Impact of Quantization on Self-Explanations
by: Wang, Qianli, et al.
Published: (2026)

Measuring Faithfulness Depends on How You Measure: Classifier Sensitivity in LLM Chain-of-Thought Evaluation
by: Young, Richard J.
Published: (2026)

Large Language Models Are Better Logical Fallacy Reasoners with Counterargument, Explanation, and Goal-Aware Prompt Formulation
by: Jeong, Jiwon, et al.
Published: (2025)

Hippocrates: An Open-Source Framework for Advancing Large Language Models in Healthcare
by: Acikgoz, Emre Can, et al.
Published: (2024)

Modeling the Data-Generating Process is Necessary for Out-of-Distribution Generalization
by: Kaur, Jivat Neet, et al.
Published: (2022)

Chain-of-Thought Reasoning In The Wild Is Not Always Faithful
by: Arcuschin, Iván, et al.
Published: (2025)

Towards Consistent Natural-Language Explanations via Explanation-Consistency Finetuning
by: Chen, Yanda, et al.
Published: (2024)

Benchmarking and Defending Against Indirect Prompt Injection Attacks on Large Language Models
by: Yi, Jingwei, et al.
Published: (2023)

Towards Trustable Language Models: Investigating Information Quality of Large Language Models
by: Rejeleene, Rick, et al.
Published: (2024)

SibylSense: Adaptive Rubric Learning via Memory Tuning and Adversarial Probing
by: Xu, Yifei, et al.
Published: (2026)

Having Beer after Prayer? Measuring Cultural Bias in Large Language Models
by: Naous, Tarek, et al.
Published: (2023)

Show Me How It's Done: The Role of Explanations in Fine-Tuning Language Models
by: Ballout, Mohamad, et al.
Published: (2024)

From Faithfulness to Correctness: Generative Reward Models that Think Critically
by: Ma, Qiyao, et al.
Published: (2025)

FaithfulSAE: Towards Capturing Faithful Features with Sparse Autoencoders without External Dataset Dependencies
by: Cho, Seonglae, et al.
Published: (2025)

Unfamiliar Finetuning Examples Control How Language Models Hallucinate
by: Kang, Katie, et al.
Published: (2024)

Transformer Circuit Faithfulness Metrics are not Robust
by: Miller, Joseph, et al.
Published: (2024)

Measuring the (Un)Faithfulness of Concept-Based Explanations
by: Kumar, Shubham, et al.
Published: (2025)

(Im)possibility of Automated Hallucination Detection in Large Language Models
by: Karbasi, Amin, et al.
Published: (2025)

Group Preference Optimization: Few-Shot Alignment of Large Language Models
by: Zhao, Siyan, et al.
Published: (2023)