paper-with-me

Papers

ER-Test: Evaluating Explanation Regularization Methods for Language Models

2022-05-25 · Brihi Joshi, Aaron Chan, Ziyi Liu, Shaoliang Nie, Maziar Sanjabi, Hamed Firooz, Xiang Ren

By explaining how humans would solve a given task, human rationales can provide strong learning signal for neural language models (LMs). Explanation regularization (ER) aims to improve LM generalization by pushing the LM's machine rationales (Which input tokens did the LM focus on?) to align with human rationales (Which input tokens would humans focus on?). Though prior works primarily study ER via in-distribution (ID) evaluation, out-of-distribution (OOD) generalization is often more critical in real-world scenarios, yet ER's effect on OOD generalization has been underexplored. In this paper, we introduce ER-Test, a framework for evaluating ER models' OOD generalization along three dimensions: unseen dataset tests, contrast set tests, and functional tests. Using ER-Test, we extensively analyze how ER models' OOD generalization varies with different ER design choices. Across two tasks and six datasets, ER-Test shows that ER has little impact on ID performance but can yield large OOD performance gains. Also, we find that ER can improve OOD performance even with limited rationale supervision. ER-Test's results help demonstrate ER's utility and establish best practices for using ER effectively.

📄 PDF Abstract BibTeX arXiv:2205.12542

Code (1)

ink-usc/er-test 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…

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…

Faithfulness Tests for Natural Language Explanations

2023-05-29 · Pepa Atanasova, Oana-Maria Camburu, Christina Lioma, Thomas Lukasiewicz 외

Explanations of neural models aim to reveal a model's decision-making process for its predictions. However, recent work shows that current methods giving explanations such as saliency maps or counterfactuals can be misle…

counterfactualDecision Making

Sanity Checks for Explanation Uncertainty

2024-03-25 · Matias Valdenegro-Toro, Mihir Mulye

Explanations for machine learning models can be hard to interpret or be wrong. Combining an explanation method with an uncertainty estimation method produces explanation uncertainty. Evaluating explanation uncertainty is…

ICE: Intervention-Consistent Explanation Evaluation with Statistical Grounding for LLMs

2026-03-19 · Abhinaba Basu, Pavan Chakraborty arxiv

Evaluating whether explanations faithfully reflect a model's reasoning remains an open problem. Existing benchmarks use single interventions without statistical testing, making it impossible to distinguish genuine faithf…

Shapley Explanation Networks

2021-04-06 · ICLR 2021 1 · Rui Wang, Xiaoqian Wang, David I. Inouye

Shapley values have become one of the most popular feature attribution explanation methods. However, most prior work has focused on post-hoc Shapley explanations, which can be computationally demanding due to its exponen…