Loading...
Can Input Attributions Explain Inductive Reasoning in In-Context Learning?
Ye, Mengyu Kuribayashi, Tatsuki Kobayashi, Goro Suzuki, Jun
Ye, Mengyu
Kuribayashi, Tatsuki
Kobayashi, Goro
Suzuki, Jun
Files
Supervisor
Department
Natural Language Processing
Embargo End Date
Type
Conference proceeding
Date
License
http://creativecommons.org/licenses/by/4.0/, http://creativecommons.org/licenses/by/4.0/
Language
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
Interpreting the internal process of neural models has long been a challenge. This challenge remains relevant in the era of large language models (LLMs) and in-context learning (ICL); for example, ICL poses a new issue of interpreting which example in the few-shot examples contributed to identifying/solving the task. To this end, in this paper, we design synthetic diagnostic tasks of inductive reasoning, inspired by the generalization tests in linguistics; here, most in-context examples are ambiguous w.r.t. their underlying rule, and one critical example disambiguates the task demonstrated. The question is whether conventional input attribution (IA) methods can track such a reasoning process, i.e., identify the influential example, in ICL. Our experiments provide several practical findings; for example, a certain simple IA method works the best, and the larger the model, the generally harder it is to interpret the ICL with gradient-based IA methods.
Citation
M. Ye, T. Kuribayashi, G. Kobayashi, J. Suzuki, "Can Input Attributions Explain Inductive Reasoning in In-Context Learning?," 2025, pp. 21199-21225.
Source
Proceedings of the Annual Meeting of the Association for Computational Linguistics
Conference
Findings of the Association for Computational Linguistics: ACL 2025
Keywords
Subjects
Source
Findings of the Association for Computational Linguistics: ACL 2025
Publisher
Association for Computational Linguistics