paper-with-me

홈 › Papers

A Necessary Step toward Faithfulness: Measuring and Improving Consistency in Free-Text Explanations

2025-05-25 · Lingjun Zhao, Hal Daumé III

Faithful free-text explanations are important to ensure transparency in high-stakes AI decision-making contexts, but they are challenging to generate by language models and assess by humans. In this paper, we present a measure for Prediction-EXplanation (PEX) consistency, by extending the concept of weight of evidence. This measure quantifies how much a free-text explanation supports or opposes a prediction, serving as an important aspect of explanation faithfulness. Our analysis reveals that more than 62% explanations generated by large language models lack this consistency. We show that applying direct preference optimization improves the consistency of generated explanations across three model families, with improvement ranging from 43.1% to 292.3%. Furthermore, we demonstrate that optimizing this consistency measure can improve explanation faithfulness by up to 9.7%.

📄 PDF Abstract BibTeX arXiv:2505.19299

Code (0)

등록된 구현이 없습니다.

Tasks

Decision Making

Similar Papers 제목 키워드 기반

On Measuring Faithfulness or Self-consistency of Natural Language Explanations

2023-11-13 · Letitia Parcalabescu, Anette Frank

Large language models (LLMs) can explain their predictions through post-hoc or Chain-of-Thought (CoT) explanations. But an LLM could make up reasonably sounding explanations that are unfaithful to its underlying reasonin…

A Comprehensive Evaluation of Multilingual Chain-of-Thought Reasoning: Performance, Consistency, and Faithfulness Across Languages

2025-10-10 · Raoyuan Zhao, Yihong Liu, Hinrich Schütze, Michael A. Hedderich arxiv

Large reasoning models (LRMs) increasingly rely on step-by-step Chain-of-Thought (CoT) reasoning to improve task performance, particularly in high-resource languages such as English. While recent work has examined final-…

Measuring Association Between Labels and Free-Text Rationales

2020-10-24 · EMNLP 2021 11 · Sarah Wiegreffe, Ana Marasović, Noah A. Smith

In interpretable NLP, we require faithful rationales that reflect the model's decision-making process for an explained instance. While prior work focuses on extractive rationales (a subset of the input words), we investi…

Decision MakingFeature ImportanceNatural Language InferenceQuestion Answering

Measuring Faithfulness of Chains of Thought by Unlearning Reasoning Steps

2025-02-20 · Martin Tutek, Fateme Hashemi Chaleshtori, Ana Marasović, Yonatan Belinkov

When prompted to think step-by-step, language models (LMs) produce a chain of thought (CoT), a sequence of reasoning steps that the model supposedly used to produce its prediction. However, despite much work on CoT promp…

Question Answering

Measuring Factual Consistency of Abstractive Summaries

2021-09-17 · ACL ARR September 2021 9 · Anonymous

Recent abstractive summarization systems fail to generate factual consistent -- faithful -- summaries, which heavily limits their practical application. Commonly, these models tend to mix concepts from the source or hal…

Abstractive Text SummarizationRe-Ranking