◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

Xinyu Li

9 papers hereh-index 5185 citations12 works total

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

author position
  • first author3
  • middle author5

Across the 8 of 9 papers where every author was matched, so the position is known.

fields
  • cs.CL4
  • cs.LG3
  • cs.AI1
  • cs.MM1
same name
  • Xinyu Li — 7 papers, h 10
  • Xinyu Li — 5 papers, h 15
  • Xinyu Li — 5 papers, h 3
  • Xinyu Li — 5 papers, h 6
  • Xinyu Li — 5 papers, h 2
  • Xinyu Li — 5 papers, h 15

Either other researchers who publish under this name, or the same person where the external sources have not merged their records.

identity via Semantic Scholar / OpenAlex

activity
20242026
collaborators
Showing cs.CLShow all

4 papers · 1 filter

cs.CL2025

ESI: Epistemic Uncertainty Quantification via Semantic-preserving Intervention for Large Language Models

Mingda Li, Xinyu Li, Weinan Zhang +1

Uncertainty Quantification (UQ) is a promising approach to improve model reliability, yet quantifying the uncertainty of Large Language Models (LLMs) is non-trivial. In this work,…

cs.CL2025

Breaking the Block: Preserving Data Continuity to Train Superior SAEs for Instruct Models

Jiaming Li, Haoran Ye, Yukun Chen +5

Sparse Autoencoders (SAEs) are a cornerstone of mechanistic interpretability. Existing training methods inherit the Block Training paradigm from LLM pre-training, which introduces…

cs.CL2024

Personalized Language Modeling from Personalized Human Feedback

Xinyu Li, Ruiyang Zhou, Zachary C. Lipton +1

Personalized large language models (LLMs) are designed to tailor responses to individual user preferences. While Reinforcement Learning from Human Feedback (RLHF) is a commonly use…

cs.CL2024

Large Language Models for Automatic Detection of Sensitive Topics

Ruoyu Wen, Stephanie Elena Crowe, Kunal Gupta +6

Sensitive information detection is crucial in content moderation to maintain safe online communities. Assisting in this traditionally manual process could relieve human moderators…

◍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.