6 citations · 7 across the 13 of their papers we have counts for
6 papers · 1 filter
Introspective X Training: Feedback Conditioning Improves Scaling Across all LLM Training Stages
Brandon Cui, Ximing Lu, Jaehun Jung +7
We tackle the question of how to scale more efficiently across the many, ever-growing stages of current LLM training pipelines. Our guiding intuition stems from the fact that the d…
MASS-DPO: Multi-negative Active Sample Selection for Direct Policy Optimization
Rohan Surana, Xintong Li, Sheldon Yu +7
Multi-negative preference optimization under the Plackett--Luce (PL) model extends Direct Preference Optimization (DPO) by leveraging comparative signals across one preferred and m…
Simultaneous Multi-objective Alignment Across Verifiable and Non-verifiable Rewards
Yiran Shen, Yu Xia, Jonathan Chang +1
Aligning large language models to human preferences is inherently multidimensional, yet most pipelines collapse heterogeneous signals into a single objective. We seek to answer wha…
A Practitioner's Guide to Multi-turn Agentic Reinforcement Learning
Ruiyi Wang, Prithviraj Ammanabrolu
We study what actually works and what doesn't for training large language models as agents via multi-turn reinforcement learning. Despite rapid progress, existing frameworks and de…
In-context Ranking Preference Optimization
Junda Wu, Rohan Surana, Zhouhang Xie +6
Recent developments in Direct Preference Optimization (DPO) allow large language models (LLMs) to function as implicit ranking models by maximizing the margin between preferred and…
Critique-out-Loud Reward Models
Zachary Ankner, Mansheej Paul, Brandon Cui +2
Traditionally, reward models used for reinforcement learning from human feedback (RLHF) are trained to directly predict preference scores without leveraging the generation capabili…