3 papers
cs.LG2025
Transformer Key-Value Memories Are Nearly as Interpretable as Sparse Autoencoders
Mengyu Ye, Jun Suzuki, Tatsuro Inaba +1
Recent interpretability work on large language models (LLMs) has been increasingly dominated by a feature-discovery approach with the help of proxy modules. Then, the quality of fe…
cs.CL2024
Can Input Attributions Explain Inductive Reasoning in In-Context Learning?
Mengyu Ye, Tatsuki Kuribayashi, Goro Kobayashi +1
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 (IC…
cs.CL2023
Assessing Step-by-Step Reasoning against Lexical Negation: A Case Study on Syllogism
Mengyu Ye, Tatsuki Kuribayashi, Jun Suzuki +2
Large language models (LLMs) take advantage of step-by-step reasoning instructions, e.g., chain-of-thought (CoT) prompting. Building on this, their ability to perform CoT-style rea…