🧑‍🔬 Shizhe Diao

🏛️ Affiliations

🏢NvidiaSanta Clara · United States2023–2026 · 16 paperscurrent🏢NvidiaReading · United Kingdom2023–2026 · 15 paperscurrent🎓University of OttawaOttawa · Canada2026 · 2 paperscurrent🎓Hong Kong University of Science and TechnologyHong Kong · Hong Kong2020–2025 · 52 papersEducation🎓University of Illinois Urbana-ChampaignUrbana · United States2023–2024 · 7 papers🎓Chinese University of Hong Kong, ShenzhenShenzhen · China2020–2023 · 4 papers🎓Wuhan UniversityWuhan · China2023–2024 · 3 papers🎓Georgia Institute of TechnologyAtlanta · United States2024–2025 · 2 papers🎓University of TorontoToronto · Canada2024 · 2 papers🎓Shanghai Jiao Tong UniversityShanghai · China2022–2023 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 9 more institutions on single bylines are not listed.

🧭 Concepts, shelves and topics

Of its works in our library: the number of works on each and its rating among them.

📅 Works by year

2020s

📄 Papers

The most cited first (OpenAlex and our library).

1. RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment (2023 · 239 citations)
   Aligning generative foundation models with human preferences usually relies on RLHF with PPO. PPO is unstable and sample-inefficient, and it must keep several large models in memory at once (policy, reference, reward, critic). The authors propose RAFT (Reward rAnked FineTuning), a simpler alternative that repeats…
2. Automatic Prompt Augmentation and Selection with Chain-of-Thought from Labeled Data (2023 · 128 citations)
   Chain-of-thought (CoT) prompting helps large language models reason, but it usually depends on hand-written rationale exemplars.
3. Mitigating the Alignment Tax of RLHF (2024 · 82 citations)
   RLHF makes LLMs follow human preferences, but it also tends to erode skills learned in pre-training. This loss is called the alignment tax. The authors measured it by aligning OpenLLaMA-3B on the Anthropic helpfulness/harmlessness data with Rejection Sampling Fine-tuning (RSF) and DPO. They then tracked performance…
4. Arithmetic Control of LLMs for Diverse User Preferences: Directional Preference Alignment with Multi-Objective Rewards (2024 · 66 citations)
   Standard RLHF compresses human judgments into one scalar reward. This pushes a model toward an "average user" and ignores people whose tastes conflict, such as those who want useful but short answers. The authors propose Directional Preference Alignment (DPA) to address this.

All works

16 works of theirs in our library, the most cited first; 4 with a page here, the others link their original until we summarise them.

1. RAFT: Reward rAnked FineTuning for Generative Foundation Model AlignmentarXiv:2304.06767Hanze Dong, Wei Xiong, Deepanshu Goyal, et al.2023 · 239 citations
2. Automatic Prompt Augmentation and Selection with Chain-of-Thought from Labeled DataFindings of the Association for Computational LinguisticsKashun Shum, Shizhe Diao, Tong Zhang2023 · 128 citations
3. R-Tuning: Instructing Large Language Models to Say ‘I Don't Know'Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers) · original ↗ · no summary yetHanning Zhang et al.2024 · 95 citations
4. Small Language Models are the Future of Agentic AIarXiv:2506.02153 · original ↗ · no summary yetPeter Belcak et al.2025 · 89 citations
5. Mitigating the Alignment Tax of RLHFConference on Empirical Methods in Natural Language Processing (EMNLP)Yong Lin, Hangyu Lin, Wei Xiong, et al.2024 · 82 citations
6. Arithmetic Control of LLMs for Diverse User Preferences: Directional Preference Alignment with Multi-Objective RewardsAnnual Meeting of the Association for Computational Linguistics (ACL)Haoxiang Wang, Yong Lin, Wei Xiong, et al.2024 · 66 citations
7. TheoremLlama: Transforming General-Purpose LLMs into Lean4 ExpertsarXiv:2407.03203 · original ↗ · no summary yetRuida Wang et al.2024 · 50 citations
8. ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language ModelsarXiv:2505.24864 · original ↗ · no summary yetMingjie Liu et al.2025 · 49 citations
9. Hymba: A Hybrid-head Architecture for Small Language ModelsarXiv:2411.13676 · original ↗ · no summary yetXin Dong et al.2024 · 49 citations
10. LLM Pruning and Distillation in Practice: The Minitron ApproacharXiv:2408.11796 · original ↗ · no summary yetSharath Turuvekere Sreenivas et al.2024 · 43 citations
11. NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning ModelarXiv:2508.14444 · original ↗ · no summary yetNVIDIA: Aarti Basant et al.2025 · 39 citations
12. UGPhysics: A Comprehensive Benchmark for Undergraduate Physics Reasoning with Large Language ModelsarXiv:2502.00334 · original ↗ · no summary yetXin Xu et al.2025 · 19 citations
13. MA-LoT: Model-Collaboration Lean-based Long Chain-of-Thought Reasoning enhances Formal Theorem ProvingarXiv:2503.03205 · original ↗ · no summary yetRuida Wang et al.2025 · 17 citations
14. Entropy-Regularized Process Reward ModelarXiv:2412.11006 · original ↗ · no summary yetHanning Zhang et al.2024 · 17 citations
15. Speech-Hands: A Self-Reflection Voice Agentic Approach to Speech Recognition and Audio Reasoning with Omni PerceptionProceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · original ↗ · no summary yetZhen Wan et al.2026
16. PROBE: PROcess-Based BEnchmark for Hallucination DetectionFindings of the Association for Computational Linguistics: ACL 2026 · original ↗ · no summary yetYu Zhang et al.2026

🤝 Co-authors here

11 co-authors with a page, the most papers together first.

• Tong Zhang ×3
• Wei Xiong ×3
• Hanze Dong ×2
• Haoxiang Wang ×2
• Jipeng Zhang ×2
• Kashun Shum ×2
• Rui Pan ×2
• Yong Lin ×2
• Han Zhao
• Hangyu Lin
• Rui Yang

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

• Annual Meeting of the Association for Computational Linguistics (ACL) ×2: ACL 2024
• Conference on Empirical Methods in Natural Language Processing (EMNLP): EMNLP 2024
• Findings of the Association for Computational Linguistics: Findings of the Association for Computational Linguistics 2023
• Findings of the Association for Computational Linguistics: ACL 2026
• Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)

🔗 Cited by

Papers of our library cite their works 792 times (of the 141,840 papers whose bibliographies we read); 45 citing papers with a page here →.

Updated 24 October 2026

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/shizhe-diao/