paper-with-me

홈 › Papers

Evaluating and Characterizing Human Rationales

2020-10-09 · EMNLP 2020 11 · Samuel Carton, Anirudh Rathore, Chenhao Tan

Two main approaches for evaluating the quality of machine-generated rationales are: 1) using human rationales as a gold standard; and 2) automated metrics based on how rationales affect model behavior. An open question, however, is how human rationales fare with these automatic metrics. Analyzing a variety of datasets and models, we find that human rationales do not necessarily perform well on these metrics. To unpack this finding, we propose improved metrics to account for model-dependent baseline performance. We then propose two methods to further characterize rationale quality, one based on model retraining and one on using "fidelity curves" to reveal properties such as irrelevance and redundancy. Our work leads to actionable suggestions for evaluating and characterizing rationales.

📄 PDF Abstract BibTeX arXiv:2010.04736

Code (1)

BoulderDS/evaluating-human-rationales 공식 구현 pytorch

Tasks

Open-Ended Question Answering

Similar Papers 제목 키워드 기반

ER-TEST Evaluating Explanation Regularization Methods for NLP Models

2022-07-01 · NAACL (TrustNLP) 2022 7 · Brihi Joshi, Aaron Chan, Ziyi Liu, Xiang Ren

Neural language models’ (NLMs’) reasoning processes are notoriously hard to explain. Recently, there has been much progress in automatically generating machine rationales of NLM behavior, but less in utilizing the ration…

Comparison of Scoring Rationales Between Large Language Models and Human Raters

2025-09-27 · Haowei Hua, Hong Jiao, Dan Song arxiv

Advances in automated scoring are closely aligned with advances in machine-learning and natural-language-processing techniques. With recent progress in large language models (LLMs), the use of ChatGPT, Gemini, Claude, an…

FRAME: Evaluating Rationale-Label Consistency Metrics for Free-Text Rationales

2022-07-02 · Aaron Chan, Shaoliang Nie, Liang Tan, Xiaochang Peng 외

Following how humans communicate, free-text rationales aim to use natural language to explain neural language model (LM) behavior. However, free-text rationales' unconstrained nature makes them prone to hallucination, so…

HallucinationLanguage Modellingtext-classificationText Classification

RORA: Robust Free-Text Rationale Evaluation

2024-02-28 · Zhengping Jiang, Yining Lu, Hanjie Chen, Daniel Khashabi 외

Free-text rationales play a pivotal role in explainable NLP, bridging the knowledge and reasoning gaps behind a model's decision-making. However, due to the diversity of potential reasoning paths and a corresponding lack…

Decision MakingDiversity

Rethinking Human Preference Evaluation of LLM Rationales

2025-09-14 · Ziang Li, Manasi Ganti, Zixian Ma, Helena Vasconcelos 외 arxiv

Large language models (LLMs) often generate natural language rationales -- free-form explanations that help improve performance on complex reasoning tasks and enhance interpretability for human users. However, evaluating…