Alert button
Picture for Bill Yuchen Lin

Bill Yuchen Lin

Alert button

SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding

Feb 14, 2024
Zhangchen Xu, Fengqing Jiang, Luyao Niu, Jinyuan Jia, Bill Yuchen Lin, Radha Poovendran

Viaarxiv icon

NovaCOMET: Open Commonsense Foundation Models with Symbolic Knowledge Distillation

Dec 10, 2023
Peter West, Ronan Le Bras, Taylor Sorensen, Bill Yuchen Lin, Liwei Jiang, Ximing Lu, Khyathi Chandu, Jack Hessel, Ashutosh Baheti, Chandra Bhagavatula, Yejin Choi

Figure 1 for NovaCOMET: Open Commonsense Foundation Models with Symbolic Knowledge Distillation
Figure 2 for NovaCOMET: Open Commonsense Foundation Models with Symbolic Knowledge Distillation
Figure 3 for NovaCOMET: Open Commonsense Foundation Models with Symbolic Knowledge Distillation
Figure 4 for NovaCOMET: Open Commonsense Foundation Models with Symbolic Knowledge Distillation
Viaarxiv icon

The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning

Dec 04, 2023
Bill Yuchen Lin, Abhilasha Ravichander, Ximing Lu, Nouha Dziri, Melanie Sclar, Khyathi Chandu, Chandra Bhagavatula, Yejin Choi

Figure 1 for The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning
Figure 2 for The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning
Figure 3 for The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning
Figure 4 for The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning
Viaarxiv icon

Lumos: Learning Agents with Unified Data, Modular Design, and Open-Source LLMs

Nov 09, 2023
Da Yin, Faeze Brahman, Abhilasha Ravichander, Khyathi Chandu, Kai-Wei Chang, Yejin Choi, Bill Yuchen Lin

Figure 1 for Lumos: Learning Agents with Unified Data, Modular Design, and Open-Source LLMs
Figure 2 for Lumos: Learning Agents with Unified Data, Modular Design, and Open-Source LLMs
Figure 3 for Lumos: Learning Agents with Unified Data, Modular Design, and Open-Source LLMs
Figure 4 for Lumos: Learning Agents with Unified Data, Modular Design, and Open-Source LLMs
Viaarxiv icon

Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Merging

Oct 17, 2023
Joel Jang, Seungone Kim, Bill Yuchen Lin, Yizhong Wang, Jack Hessel, Luke Zettlemoyer, Hannaneh Hajishirzi, Yejin Choi, Prithviraj Ammanabrolu

Viaarxiv icon

Suspicion-Agent: Playing Imperfect Information Games with Theory of Mind Aware GPT-4

Oct 06, 2023
Jiaxian Guo, Bo Yang, Paul Yoo, Bill Yuchen Lin, Yusuke Iwasawa, Yutaka Matsuo

Figure 1 for Suspicion-Agent: Playing Imperfect Information Games with Theory of Mind Aware GPT-4
Figure 2 for Suspicion-Agent: Playing Imperfect Information Games with Theory of Mind Aware GPT-4
Figure 3 for Suspicion-Agent: Playing Imperfect Information Games with Theory of Mind Aware GPT-4
Figure 4 for Suspicion-Agent: Playing Imperfect Information Games with Theory of Mind Aware GPT-4
Viaarxiv icon

TIGERScore: Towards Building Explainable Metric for All Text Generation Tasks

Oct 01, 2023
Dongfu Jiang, Yishan Li, Ge Zhang, Wenhao Huang, Bill Yuchen Lin, Wenhu Chen

Figure 1 for TIGERScore: Towards Building Explainable Metric for All Text Generation Tasks
Figure 2 for TIGERScore: Towards Building Explainable Metric for All Text Generation Tasks
Figure 3 for TIGERScore: Towards Building Explainable Metric for All Text Generation Tasks
Figure 4 for TIGERScore: Towards Building Explainable Metric for All Text Generation Tasks
Viaarxiv icon

LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition

Jul 25, 2023
Chengsong Huang, Qian Liu, Bill Yuchen Lin, Tianyu Pang, Chao Du, Min Lin

Figure 1 for LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition
Figure 2 for LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition
Figure 3 for LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition
Figure 4 for LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition
Viaarxiv icon

LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion

Jun 10, 2023
Dongfu Jiang, Xiang Ren, Bill Yuchen Lin

Figure 1 for LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion
Figure 2 for LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion
Figure 3 for LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion
Figure 4 for LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion
Viaarxiv icon

Faith and Fate: Limits of Transformers on Compositionality

Jun 01, 2023
Nouha Dziri, Ximing Lu, Melanie Sclar, Xiang Lorraine Li, Liwei Jiang, Bill Yuchen Lin, Peter West, Chandra Bhagavatula, Ronan Le Bras, Jena D. Hwang, Soumya Sanyal, Sean Welleck, Xiang Ren, Allyson Ettinger, Zaid Harchaoui, Yejin Choi

Figure 1 for Faith and Fate: Limits of Transformers on Compositionality
Figure 2 for Faith and Fate: Limits of Transformers on Compositionality
Figure 3 for Faith and Fate: Limits of Transformers on Compositionality
Figure 4 for Faith and Fate: Limits of Transformers on Compositionality
Viaarxiv icon