12 papers
Selective LoRA for Visual Tokens and Attention Heads
Tiange Luo, Lajanugen Logeswaran, Jaekyeom Kim +2
Low-rank adaptation (LoRA) is widely used for parameter-efficient fine-tuning, but its standard all-token, all-head design ignores the heterogeneous structure of vision language mo…
SPRIG: Improving Large Language Model Performance by System Prompt Optimization
Lechen Zhang, Tolga Ergen, Lajanugen Logeswaran +2
Large Language Models (LLMs) have shown impressive capabilities in many scenarios, but their performance depends, in part, on the choice of prompt. Past research has focused on opt…
Scaling Web Agent Training through Automatic Data Generation and Fine-grained Evaluation
Lajanugen Logeswaran, Jaekyeom Kim, Sungryull Sohn +2
We present a scalable pipeline for automatically generating high-quality training data for web agents. In particular, a major challenge in identifying high-quality training instanc…
Gaming the Judge: Unfaithful Chain-of-Thought Can Undermine Agent Evaluation
Muhammad Khalifa, Lajanugen Logeswaran, Jaekyeom Kim +6
Large language models (LLMs) are increasingly used as judges to evaluate agent performance, particularly in non-verifiable settings where judgments rely on agent trajectories inclu…
GRACE: Discriminator-Guided Chain-of-Thought Reasoning
Muhammad Khalifa, Lajanugen Logeswaran, Moontae Lee +2
In the context of multi-step reasoning, e.g., with chain-of-thought, language models (LMs) can easily assign a high likelihood to incorrect steps. As a result, decoding strategies…
Process Reward Models That Think
Muhammad Khalifa, Rishabh Agarwal, Lajanugen Logeswaran +5
Step-by-step verifiers -- also known as process reward models (PRMs) -- are a key ingredient for test-time scaling. PRMs require step-level supervision, making them expensive to tr…