Pinjia He
- Papers
- 8
Cite
Notes
Only stored in your browser.
8papers
Authored papers
8The Pensieve Paradigm: Stateful Language Models Mastering Their Own Context
arXiv 2026
UTBoost: Rigorous Evaluation of Coding Agents on SWE-Bench
arXiv 2025
Trust, But Verify: A Self-Verification Approach to Reinforcement Learning with Verifiable Rewards
arXiv 2025
LogicAsker: Evaluating and Improving the Logical Reasoning Ability of Large Language Models
arXiv 2024
Difficult Task Yes but Simple Task No: Unveiling the Laziness in Multimodal LLMs
arXiv 2024
Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training
arXiv 2024
GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher
arXiv 2023
BiasAsker: Measuring the Bias in Conversational AI System
arXiv 2023
Affiliations
No known affiliations.
Frequent co-authors
10from 8 papers