Profiles2024-2026
Hao Peng
University of Illinois Urbana -Champaign
14Papers
10Last author
26Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers14
- Good SFT Optimizes for SFT, Better SFT Prepares for Reinforcement LearningAuthor 5 of 5ICML 2026 · 8 citations
- The Unreasonable Effectiveness of Entropy Minimization in LLM ReasoningAuthor 5 of 5NeurIPS 2025 · 185 citations
- The Best Instruction-Tuning Data are Those That FitAuthor 3 of 3NeurIPS 2025 · 59 citations
- Reinforcement Learning Finetunes Small Subnetworks in Large Language ModelsAuthor 4 of 4NeurIPS 2025 · 43 citations
- Context Length Alone Hurts LLM Performance Despite Perfect RetrievalAuthor 10 of 10EMNLP Findings 2025 · 38 citations
- FACTCHECKMATE: Preemptively Detecting and Mitigating Hallucinations in LMsAuthor 4 of 4EMNLP Findings 2025 · 3 citations
- Improving Influence-based Instruction Tuning Data Selection for Balanced Learning of Diverse CapabilitiesAuthor 4 of 4EMNLP Findings 2025 · 1 citation
- A Little Goes a Long Way: Efficient Long Context Training and Inference with Partial ContextsAuthor 5 of 5ICLR 2025
- Retrieval Head Mechanistically Explains Long-Context FactualityAuthor 4 of 5ICLR 2025
- MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language FeedbackAuthor 6 of 7ICLR 2024 · 308 citations
- Data Engineering for Scaling Language Models to 128K ContextAuthor 7 of 7ICML 2024 · 204 citations
- CRAFT: Customizing LLMs by Creating and Retrieving from Specialized ToolsetsAuthor 5 of 6ICLR 2024 · 117 citations
- TRAM: Bridging Trust Regions and Sharpness Aware MinimizationAuthor 4 of 4ICLR 2024 · 6 citations
- ActionIE: Action Extraction from Scientific Literature with Programming LanguagesAuthor 7 of 9ACL 2024
