◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

Chujie Zheng

Tsinghua University

29 papers hereh-index 2510.3k citations34 works total

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

author position
  • first author12
  • middle author16

Across the 28 of 29 papers where every author was matched, so the position is known.

fields
  • cs.CL21
  • cs.AI4
  • cs.LG3
  • cs.CR1
affiliations
  • Tsinghua University
Homepage
same name
  • Chujie Zheng — 6 papers, h 3
  • Chujie Zheng — 4 papers, h 5
  • Chujie Zheng — 4 papers, h 1
  • Chujie Zheng — 3 papers, h 1

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
20192025
most citedQwen3 Technical Report

111 citations · 273 across the 27 of their papers we have counts for

collaborators
Showing 2024Show all

4 papers · 1 filter

cs.AI2024★ 1 cited

ProcessBench: Identifying Process Errors in Mathematical Reasoning

Chujie Zheng, Zhenru Zhang, Beichen Zhang +6

As language models regularly make mistakes when solving math problems, automated identification of errors in the reasoning process becomes increasingly significant for their scalab…

cs.CR2024★ 2 cited

From Theft to Bomb-Making: The Ripple Effect of Unlearning in Defending Against Jailbreak Attacks

Zhexin Zhang, Junxiao Yang, Yida Lu +5

Large Language Models (LLMs) are known to be vulnerable to jailbreak attacks. An important observation is that, while different types of jailbreak attacks can generate significantl…

cs.LG2024★ 1 cited

Model Extrapolation Expedites Alignment

Chujie Zheng, Ziqi Wang, Heng Ji +2

Given the high computational cost of preference alignment training of large language models (LLMs), exploring efficient methods to reduce the training overhead remains an important…

cs.LG2024★ 6 cited

On Prompt-Driven Safeguarding for Large Language Models

Chujie Zheng, Fan Yin, Hao Zhou +5

Prepending model inputs with safety prompts is a common practice for safeguarding large language models (LLMs) against queries with harmful intents. However, the underlying working…

◍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.