arXiv Computation and Language

An Empirical Study of Counterfactual Self-Explanations in LLMs

The paper investigates counterfactual self‑explanations in large language models, where a model edits an input minimally to change its own prediction. Experiments on sentiment analysis and natural language inference with ten instruction‑tuned models from the LLaMA‑3 and Qwen‑2.5 families show that larger models produce more faithful, minimal, and human‑aligned counterfactuals. While rationale‑guided prompts improve minimality and alignment, they do not consistently enhance faithfulness, indicating that explanation quality depends heavily on model capacity and requires empirical validation.

arXiv AI

Aug 26

Can Large Language Models Still Explain Themselves? Investigating the Impact of Quantization on Self-Explanations

The paper investigates how quantization affects large language models’ self‑explanations, examining natural language explanations and counterfactual examples across three quantization techniques and bit widths. Results show moderate declines in explanation quality (up to 4.4%) and faithfulness (up to 3.9%), with user studies indicating up to an 8.5% drop in coherence and trustworthiness. Larger models are less resilient in quality but remain more faithful, and no single quantization method consistently outperforms others across accuracy, quality, and faithfulness.

By Qianli Wang, Nils Feldhus, Pepa Atanasova, Fedor Splitt, Simon Ostermann, Sebastian M\"oller, Vera Schmitt

llms efficiency

arXiv AI

Jul 2

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

arXiv:2503. 13445v3 Announce Type: replace-cross Abstract: When asked to explain their decisions, LLMs can often give explanations which sound plausible to humans.

By Noah Y. Siegel, Nicolas Heess, Maria Perez-Ortiz, Oana-Maria Camburu

llms

arXiv AI

Jun 6

Macro: Enhancing Multilingual Counterfactual Explanations through Alignment-as-Preference Optimization

arXiv:2605. 11632v2 Announce Type: replace-cross Abstract: Self-generated counterfactual explanations (SCEs) are minimally modified inputs (minimality) generated by large language models (LLMs) that flip their own predictions (validity), offering a causally grounded approach to unraveling black-box LLM behavior.

By Yilong Wang, Qianli Wang, Bohao Chu, Yihong Liu, Jing Yang, Simon Ostermann

llms reinforcement-learning fine-tuning safety

arXiv Machine Learning

Aug 27

iFlip: Iterative Feedback-driven Counterfactual Example Refinement

iFlip is an iterative refinement method for generating counterfactual examples using large language models. It incorporates three feedback types—model confidence, feature attribution, and natural language—to guide successive edits. Experiments show iFlip outperforms five state‑of‑the‑art baselines, achieving a 57.8% higher validity rate and improving model performance through counterfactual data augmentation.

By Yilong Wang, Qianli Wang, Nils Feldhus

llms nlp benchmarks

arXiv AI

Jul 24

Training Large Language Models for Self-Explanation Faithfulness

arXiv:2607. 21090v1 Announce Type: cross Abstract: We propose a Reinforcement Learning (RL) method to directly optimize the faithfulness of self-explanations - the extent to which a model's generated reasoning accurately reflects its internal decision-making process.

By Yeoktatt Cheah, Mar\'ia P\'erez-Ortiz, Noah Y. Siegel, Oana-Maria Camburu

llms reinforcement-learning fine-tuning safety

arXiv AI

Jun 30

What LLMs explain is not what they believe: Evaluating explanation sufficiency under models' own input beliefs

arXiv:2606. 28615v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed in high-stakes domains, where free-text explanations such as chain-of-thought and post-hoc rationales are used to justify model outputs.

By Nhi Nguyen, Shauli Ravfogel, Rajesh Ranganath

llms

arXiv AI

Aug 18

Would this change your answer? Evaluating Explanations of LLM Behavior In The Wild with Counterfactual Experiments

arXiv:2608. 16747v1 Announce Type: cross Abstract: Many areas of AI research, such as language model interpretability and chain of thought faithfulness, seek to explain model behaviors.

By Adam Karvonen, Euan Ong, Subhash Kantamneni, Samuel Marks

llms agents safety

arXiv AI

Aug 18

When Do Explanations Help In-Context Learning? A Comparative Study of Natural Language Explanation Types and Faithfulness

arXiv:2608. 16627v1 Announce Type: cross Abstract: Natural language explanations (NLEs) are increasingly used as inputs, for example, as few-shot rationales that influence model behavior in in-context learning (ICL).

By Mahdi Dhaini, Adam Dejl, Juraj Vladika, Volkan \"Ozer, Barbara Plank, Gjergji Kasneci

llms benchmarks safety

arXiv Computation and Language

Sep 7

From Plausible to Actionable: A Position on LLM Self-Explanations

The paper discusses how Large Language Models can produce natural language self‑explanations that appear plausible but may not accurately reflect the model’s reasoning. It critiques current evaluation methods for such explanations and offers practical guidelines to assess their plausibility and faithfulness. Additionally, it argues that evaluation should also consider the actionability of these explanations, showing how they can aid decision‑making for various stakeholders.

By Elize Herrewijnen, Benedetta Muscato, Gizem Gezici, Fosca Giannotti

llms

arXiv Machine Learning

Jul 27

CEL: Comprehensive Counterfactual Explanations Library and Benchmark

arXiv:2607. 22045v1 Announce Type: new Abstract: Counterfactual explanations are a prominent approach in explainable artificial intelligence (xAI), providing actionable guidance on what input changes would alter a model's prediction to a desired outcome.

By Oleksii Furman, {\L}ukasz Lenkiewicz, Marcel Musia{\l}ek, Maciej Zi\k{e}ba

efficiency benchmarks

arXiv AI

Jul 1

Introspective Coupling: Self-Explanation Training Tracks Behavioral Change Despite Fixed Supervision

arXiv:2606. 32038v1 Announce Type: cross Abstract: When does training language models (LMs) to generate explanations of their predictions yield faithful introspection, rather than superficial imitation?

By Zifan Carl Guo, Laura Ruis, Jacob Andreas, Belinda Z. Li

llms

arXiv Computation and Language

1d ago

An Analysis of Training-Free Self-Reported Confidence in Language Models

arXiv:2609.20541v1 Announce Type: new Abstract: Large language models can report a numerical confidence together with generated content, but it is unclear whether this report is more than calibrated...

By Lukas Meyer, Sofia Rossi, Wei Chen, Thomas Laurent, Yiming Li

llms benchmarks

Related stories