◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

Chengzhi Hu

4 papers hereh-index 4135 citations4 works total

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

author position
  • middle author4

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

fields
  • cs.CL4
same name
  • Chengzhi Hu — 2 papers, h 1
  • Chengzhi Hu — 1 paper, h 0
  • Chengzhi Hu — 1 paper, h 5
  • Chengzhi Hu — 1 paper, h 14

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

4 papers

cs.CL2026

Languages in Whisper-Style Speech Encoders Align Both Phonetically and Semantically

Ryan Soh-Eun Shim, Domenico De Cristofaro, Chengzhi Martin Hu +2

Cross-lingual alignment in pretrained language models enables knowledge transfer across languages. Similar alignment has been reported in Whisper-style speech encoders, based on sp…

cs.CL2025

Surgical, Cheap, and Flexible: Mitigating False Refusal in Language Models via Single Vector Ablation

Xinpeng Wang, Chengzhi Hu, Paul Röttger +1

Training a language model to be both helpful and harmless requires careful calibration of refusal behaviours: Models should refuse to follow malicious instructions or give harmful…

cs.CL2024

Look at the Text: Instruction-Tuned Language Models are More Robust Multiple Choice Selectors than You Think

Xinpeng Wang, Chengzhi Hu, Bolei Ma +2

Multiple choice questions (MCQs) are commonly used to evaluate the capabilities of large language models (LLMs). One common way to evaluate the model response is to rank the candid…

cs.CL2024

"My Answer is C": First-Token Probabilities Do Not Match Text Answers in Instruction-Tuned Language Models

Xinpeng Wang, Bolei Ma, Chengzhi Hu +5

The open-ended nature of language generation makes the evaluation of autoregressive large language models (LLMs) challenging. One common evaluation approach uses multiple-choice qu…

◍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.