Bill Yuchen Lin
Meta FAIR research scientist; previously AI2; created WildBench, WildChat, ZebraLogic.
- Role
- researcher
- Currently at
- Meta FAIR (Fundamental AI Research)
- twitter.com/billyuchenlin
- GitHub
- github.com/yuchenlin
- Scholar
- scholar.google.com/citations
- Papers
- 20
Cite
Notes
Only stored in your browser.
Authored papers
20TinyV: Reducing False Negatives in Verification Improves RL for LLM Reasoning
arXiv 2025
Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing
preprint
RewardBench: Evaluating Reward Models for Language Modeling
arXiv 2024
WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs
arXiv 2024
The Good, The Bad, and The Greedy: Evaluation of LLMs Should Not Ignore Non-Determinism
arXiv 2024
ASCIIEval: Benchmarking Models' Visual Perception in Text Strings via ASCII Art
arXiv 2024
ChatBug: A Common Vulnerability of Aligned LLMs Induced by Chat Templates
arXiv 2024
WildBench: Benchmarking LLMs with Challenging Tasks from Real Users in the Wild
arXiv 2024
Trial and Error: Exploration-Based Trajectory Optimization for LLM Agents
arXiv 2024
SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding
arXiv 2024
LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition
arXiv 2023
Faith and Fate: Limits of Transformers on Compositionality
faith-and-fate-limits-of-transformers-on
Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Merging
arXiv 2023
Agent Lumos: Unified and Modular Training for Open-Source Language Agents
arXiv 2023
Inference-Time Policy Adapters (IPA): Tailoring Extreme-Scale LMs without Fine-tuning
arXiv 2023
LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion
arXiv 2023
Suspicion-Agent: Playing Imperfect Information Games with Theory of Mind Aware GPT-4
arXiv 2023
TIGERScore: Towards Building Explainable Metric for All Text Generation Tasks
arXiv 2023
Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
TMLR
Common Sense Beyond English: Evaluating and Improving Multilingual Language Models for Commonsense Reasoning
ACL 2021 5
Affiliations
Previously
Frequent co-authors
10from 20 papers
Yejin Choi
professor
Nouha Dziri
researcher
Xiang Ren
professor
Fengqing Jiang
grad-student
Khyathi Chandu
Luyao Niu
researcher
Radha Poovendran
professor
Zhangchen Xu
grad-student
Abhilasha Ravichander
Faeze Brahman
researcher