cs.AI updates on arXiv.org 10月28日 12:12
RACE框架评估LLM解释的合理性
index_new5.html
../../../zaker_core/zaker_tpl_static/wap/tpl_guoji1.html

 

本文提出RACE框架,用于评估LLM生成的解释与可解释特征重要性之间的对齐,分析四个文本分类数据集,发现LLM解释结合了表面证据和灵活证据重用,但可能放大误导性线索。

arXiv:2510.21884v1 Announce Type: cross Abstract: The growing adoption of machine learning (ML) in sensitive domains has heightened the demand for transparent and interpretable artificial intelligence. Large Language Models (LLMs) are increasingly capable of producing natural language explanations, yet it remains unclear whether these rationales faithfully capture the predictive signals that underlie decisions. This paper introduces RACE-Reasoning Alignment for Completeness of Explanations, a systematic framework to evaluate the alignment between LLM-generated explanations and interpretable feature importance scores derived from a logistic regression baseline. We analyze four widely used text classification datasets-WIKI ONTOLOGY, AG NEWS, IMDB, and GOEMOTIONS-and compare LLM rationales against top-ranked supporting and contradicting lexical features. To capture alignment at multiple levels of granularity, RACE implements token-aware, exact string, and edit-distance matching techniques. Empirical results reveal a consistent asymmetry: correct predictions exhibit higher coverage of supporting features, while incorrect predictions are associated with elevated coverage of contradicting features. Edit-distance matching further uncovers paraphrastic overlaps, boosting coverage while preserving this asymmetry. These findings demonstrate that LLM rationales combine both surface-level and flexible evidence reuse, yet can also amplify misleading cues in error cases. RACE provides new insights into the faithfulness of LLM explanations and establishes a quantitative basis for evaluating reasoning completeness in neural language models.

Fish AI Reader

Fish AI Reader

AI辅助创作,多种专业模板,深度分析,高质量内容生成。从观点提取到深度思考,FishAI为您提供全方位的创作支持。新版本引入自定义参数,让您的创作更加个性化和精准。

FishAI

FishAI

鱼阅,AI 时代的下一个智能信息助手,助你摆脱信息焦虑

联系邮箱 441953276@qq.com

相关标签

LLM 解释对齐 RACE框架 文本分类 特征重要性
相关文章