◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

Tatsuro Inaba

4 papers hereh-index 353 citations5 works total

Matching runs newest-first, so older work may not be attached to this profile yet.

author position
  • middle author3

Across the 3 of 4 papers where every author was matched, so the position is known.

fields
  • cs.CL3
  • cs.LG1

identity via Semantic Scholar / OpenAlex

collaborators

4 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.CL2025

How a Bilingual LM Becomes Bilingual: Tracing Internal Representations with Sparse Autoencoders

Tatsuro Inaba, Go Kamoda, Kentaro Inui +5

This study explores how bilingual language models develop complex internal representations. We employ sparse autoencoders to analyze internal representations of bilingual language…

cs.CL2025

TopK Language Models

Ryosuke Takahashi, Tatsuro Inaba, Kentaro Inui +1

Sparse autoencoders (SAEs) have become an important tool for analyzing and interpreting the activation space of transformer-based language models (LMs). However, SAEs suffer severa…

cs.CL2025

Weight-based Analysis of Detokenization in Language Models: Understanding the First Stage of Inference Without Inference

Go Kamoda, Benjamin Heinzerling, Tatsuro Inaba +3

According to the stages-of-inference hypothesis, early layers of language models map their subword-tokenized input, which does not necessarily correspond to a linguistically meanin…

◍wovepaper

Papers, researchers and institutions, woven together.

Explore
  • Search
  • Researchers
  • Institutions
Account
  • Library
  • Chat
Data
  • arXiv.org
  • Semantic Scholar
  • OpenAlex
  • Latest RSS
AboutContactPrivacyDevelopersllms.txtopenapi.json
Not affiliated with arXiv. Researcher data from Semantic Scholar (ODC-BY) and OpenAlex.