565 citations · 938 across the 45 of their papers we have counts for
46 papers
Latent Action Pretraining from Videos
Seonghyeon Ye, Joel Jang, Byeongguk Jeon +13
We introduce Latent Action Pretraining for general Action models (LAPA), an unsupervised method for pretraining Vision-Language-Action (VLA) models without ground-truth robot actio…
WildVision: Evaluating Vision-Language Models in the Wild with Human Preferences
Yujie Lu, Dongfu Jiang, Wenhu Chen +3
Recent breakthroughs in vision-language models (VLMs) emphasize the necessity of benchmarking human preferences in real-world multimodal interactions. To address this gap, we launc…
Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing
Zhangchen Xu, Fengqing Jiang, Luyao Niu +4
High-quality instruction data is critical for aligning large language models (LLMs). Although some models, such as Llama-3-Instruct, have open weights, their alignment data remain…
WildBench: Benchmarking LLMs with Challenging Tasks from Real Users in the Wild
Bill Yuchen Lin, Yuntian Deng, Khyathi Chandu +6
We introduce WildBench, an automated evaluation framework designed to benchmark large language models (LLMs) using challenging, real-world user queries. WildBench consists of 1,024…
RewardBench: Evaluating Reward Models for Language Modeling
Nathan Lambert, Valentina Pyatkin, Jacob Morrison +9
Reward models (RMs) are at the crux of successfully using RLHF to align pretrained models to human preferences, yet there has been relatively little study that focuses on evaluatio…
Trial and Error: Exploration-Based Trajectory Optimization for LLM Agents
Yifan Song, Da Yin, Xiang Yue +3
Large Language Models (LLMs) have become integral components in various autonomous agent systems. In this study, we present an exploration-based trajectory optimization approach, r…
SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding
Zhangchen Xu, Fengqing Jiang, Luyao Niu +3
As large language models (LLMs) become increasingly integrated into real-world applications such as code generation and chatbot assistance, extensive efforts have been made to alig…
The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning
Bill Yuchen Lin, Abhilasha Ravichander, Ximing Lu +5
The alignment tuning process of large language models (LLMs) typically involves instruction learning through supervised fine-tuning (SFT) and preference tuning via reinforcement le…
Agent Lumos: Unified and Modular Training for Open-Source Language Agents
Da Yin, Faeze Brahman, Abhilasha Ravichander +4
Closed-source agents suffer from several issues such as a lack of affordability, transparency, and reproducibility, particularly on complex interactive tasks. This motivates the de…
Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Merging
Joel Jang, Seungone Kim, Bill Yuchen Lin +6
While Reinforcement Learning from Human Feedback (RLHF) aligns Large Language Models (LLMs) with general, aggregate human preferences, it is suboptimal for learning diverse, indivi…
TIGERScore: Towards Building Explainable Metric for All Text Generation Tasks
Dongfu Jiang, Yishan Li, Ge Zhang +3
We present TIGERScore, a \textbf{T}rained metric that follows \textbf{I}nstruction \textbf{G}uidance to perform \textbf{E}xplainable, and \textbf{R}eference-free evaluation over a…
Suspicion-Agent: Playing Imperfect Information Games with Theory of Mind Aware GPT-4
Jiaxian Guo, Bo Yang, Paul Yoo +3
Unlike perfect information games, where all elements are known to every player, imperfect information games emulate the real-world complexities of decision-making under uncertain o…
LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition
Chengsong Huang, Qian Liu, Bill Yuchen Lin +3
Low-rank adaptations (LoRA) are often employed to fine-tune large language models (LLMs) for new tasks. This paper investigates LoRA composability for cross-task generalization and…
LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion
Dongfu Jiang, Xiang Ren, Bill Yuchen Lin
We present LLM-Blender, an ensembling framework designed to attain consistently superior performance by leveraging the diverse strengths of multiple open-source large language mode…
Faith and Fate: Limits of Transformers on Compositionality
Nouha Dziri, Ximing Lu, Melanie Sclar +13
Transformer large language models (LLMs) have sparked admiration for their exceptional performance on tasks that demand intricate multi-step reasoning. Yet, these models simultaneo…
SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks
Bill Yuchen Lin, Yicheng Fu, Karina Yang +6
We introduce SwiftSage, a novel agent framework inspired by the dual-process theory of human cognition, designed to excel in action planning for complex interactive reasoning tasks…
Inference-Time Policy Adapters (IPA): Tailoring Extreme-Scale LMs without Fine-tuning
Ximing Lu, Faeze Brahman, Peter West +14
While extreme-scale language models have demonstrated exceptional performance on a variety of language tasks, the degree of control over these language models through pure promptin…
PairReranker: Pairwise Reranking for Natural Language Generation
Dongfu Jiang, Bill Yuchen Lin, Xiang Ren
Pre-trained language models have been successful in natural language generation (NLG) tasks. While various decoding methods have been employed, they often produce suboptimal result…
Reflect, Not Reflex: Inference-Based Common Ground Improves Dialogue Response Quality
Pei Zhou, Hyundong Cho, Pegah Jandaghi +4
Human communication relies on common ground (CG), the mutual knowledge and beliefs shared by participants, to produce coherent and interesting conversations. In this paper, we demo…
On Grounded Planning for Embodied Tasks with Language Models
Bill Yuchen Lin, Chengsong Huang, Qian Liu +3
Language models (LMs) have demonstrated their capability in possessing commonsense knowledge of the physical world, a crucial aspect of performing tasks in everyday life. However,…
Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
Aarohi Srivastava, Abhinav Rastogi, Abhishek Rao +448
Language models demonstrate both quantitative improvement and new qualitative capabilities with increasing scale. Despite their potentially transformative impact, these new capabil…
On Continual Model Refinement in Out-of-Distribution Data Streams
Bill Yuchen Lin, Sida Wang, Xi Victoria Lin +4
Real-world natural language processing (NLP) models need to be continually updated to fix the prediction errors in out-of-distribution (OOD) data streams while overcoming catastrop…
Unsupervised Cross-Task Generalization via Retrieval Augmentation
Bill Yuchen Lin, Kangmin Tan, Chris Miller +2
Humans can perform unseen tasks by recalling relevant skills acquired previously and then generalizing them to the target tasks, even if there is no supervision at all. In this pap…
On the Robustness of Reading Comprehension Models to Entity Renaming
Jun Yan, Yang Xiao, Sagnik Mukherjee +3
We study the robustness of machine reading comprehension (MRC) models to entity renaming -- do models make more wrong predictions when the same questions are asked about an entity…