Zhixue Zhao

Lecturer@University of Sheffield, University of Sheffield·英国·OpenReview

研究方向

model editing · model hallucination · model pruning · quantization · text-to-image models · model compression · multilingual LLMs · model interpretability

5.5

PerSpectra: A Scalable and Configurable Pluralist Benchmark of Perspectives from Arguments

ICLR 2026Poster

5.0

Investigating Language-Specific Calibration For Pruning Multilingual Large Language Models

ICLR 2025Withdrawn

通讯

5.3

ScImage: How good are multimodal large language models at scientific text-to-image generation?

ICLR 2025Poster

通讯

3.8

RULEBREAKERS: Challenging LLMs at the Crossroads between Formal Logic and Human-like Reasoning

合作者 (20)

Zhixue Zhao

PerSpectra: A Scalable and Configurable Pluralist Benchmark of Perspectives from Arguments

Tracing and Reversing Edits in LLMs

Can Confidence Estimates Decide When Chain-of-Thought is Necessary for LLMs?

OpenReviewer: Predicting Conference Decisions with LLMs and Beyond

Quantifying Edits Decay in Fine-tuned LLMs

On the Robustness of Model Edits under Fine-Tuning in Text-to-Image Models

Investigating Language-Specific Calibration For Pruning Multilingual Large Language Models

ScImage: How good are multimodal large language models at scientific text-to-image generation?

RULEBREAKERS: Challenging LLMs at the Crossroads between Formal Logic and Human-like Reasoning