15 papers
Inverse RL Helps Align AI by Imitating Humans
MichaÅ WiliÅski, Liu Leqi, Chirag Nagpal
Language model alignment aims to make model behavior reliably reflect desirable properties such as helpfulness, safety, and instruction following. Current approaches typically use…
The Severance Problem: LLMs are Unaware of the Person Beyond the Prompt
Dor Litvak, Liu Leqi
The paper identifies the "Severance Problem"—the lack of an explicit representation of a user beyond the prompt—in current LLM-based personal assistants, and proposes a "Severance…
Evaluating Stochasticity in Deep Research Agents
Haotian Zhai, Elias Stengel-Eskin, Pratik Patil +1
Deep Research Agents (DRAs) are promising agentic systems that gather and synthesize information to support research across domains such as financial decision-making, medical analy…
Learning Robust Reasoning through Guided Adversarial Self-Play
Shuozhe Li, Vaishnav Tadiparthi, Kwonjoon Lee +6
Reinforcement learning from verifiable rewards (RLVR) produces strong reasoning models, yet they can fail catastrophically when the conditioning context is fallible (e.g., corrupte…
ExPO: Unlocking Hard Reasoning with Self-Explanation-Guided Reinforcement Learning
Ruiyang Zhou, Shuozhe Li, Amy Zhang +1
Self-improvement via RL often fails on complex reasoning tasks because GRPO-style post-training methods rely on the model's initial ability to generate positive samples. Without gu…
Position: Thematic Analysis of Unstructured Clinical Transcripts with Large Language Models
Seungjun Yi, Joakim Nguyen, Terence Lim +8
This position paper examines how large language models (LLMs) can support thematic analysis of unstructured clinical transcripts, a widely used but resource-intensive method for un…