4 citations · 21 across the 53 of their papers we have counts for
7 papers · 1 filter
Understanding the Synergy between SFT, RLVR, and OPD in LLM Post-Training
Emre Can Acikgoz, Yang Li, Zeyu Leo Liu +4
Modern LLM post-training composes supervised fine-tuning (SFT), reinforcement learning with verifiable rewards (RLVR), and on-policy distillation (OPD) into multi-stage pipelines,…
Do We Need Adam? Surprisingly Strong and Sparse Reinforcement Learning with SGD in LLMs
Sagnik Mukherjee, Lifan Yuan, Pavan Jayasinha +2
Reinforcement learning (RL), particularly RL from verifiable reward (RLVR), has become a crucial phase of training large language models (LLMs) and a key focus of current scaling e…
Self-Improving LLM Agents at Test-Time
Emre Can Acikgoz, Cheng Qian, Heng Ji +2
One paradigm of language model (LM) fine-tuning relies on creating large training datasets, under the assumption that high quantity and diversity will enable models to generalize t…
SIMU: Selective Influence Machine Unlearning
Anu Agarwal, Mihir Pamnani, Dilek Hakkani-Tur
The undesired memorization of sensitive information by Large Language Models (LLMs) has emphasized the need for safety mechanisms that can regulate model behavior. This has led to…
Reinforcement Learning Finetunes Small Subnetworks in Large Language Models
Sagnik Mukherjee, Lifan Yuan, Dilek Hakkani-Tur +1
Reinforcement learning (RL) yields substantial improvements in large language models (LLMs) downstream task performance and alignment with human values. Surprisingly, such large ga…
ToolRL: Reward is All Tool Learning Needs
Cheng Qian, Emre Can Acikgoz, Qi He +5
Current Large Language Models (LLMs) often undergo supervised fine-tuning (SFT) to acquire tool use capabilities. However, SFT struggles to generalize to unfamiliar or complex tool…
Neural Networks for Learnable and Scalable Influence Estimation of Instruction Fine-Tuning Data
Ishika Agarwal, Dilek Hakkani-Tür
Influence functions provide crucial insights into model training, but existing methods suffer from large computational costs and limited generalization. Particularly, recent works…