Chengzhi Li
4 papers · 2025–2026 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
π Conference Polyglot (3) π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (10) π§ Keyword Pioneer π Cross-Pollinator (15)
β
The Questioner
Conferences
ACL (2)
EMNLP (1)
NAACL (1)
Top co-authors
Keywords
large language model
(3)
causal effect
(2)
bias mitigation
(1)
vision-language model
(1)
value alignment
(1)
attention head
(1)
arithmetic computation
(1)
representation editing
(1)
causal intervention
(1)
multiple choice question answering
(1)
llm alignment
(1)
layer-wise probing
(1)
spatial intelligence
(1)
mechanistic analysis
(1)
causal debiasing
(1)
option symbol bia
(1)
mixed arithmetic
(1)
causal effect driven fine-tuning
(1)
anchor words tuning
(1)
logits difference
(1)
Papers
How Do LLMs and VLMs Understand Viewpoint Rotation Without Vision? An Interpretability Study
ACL 2026
Memory or Reasoning? Explore How LLMs Compute Mixed Arithmetic Expressions
ACL 2025
Constructing Your Modelβs Value Distinction: Towards LLM Alignment with Anchor Words Tuning
EMNLP 2025
Option Symbol Matters: Investigating and Mitigating Multiple-Choice Option Symbol Bias of Large Language Models
NAACL 2025