6 papers · 1 filter
Let's (not) just put things in Context: Test-Time Training for Long-Context LLMs
Rachit Bansal, Aston Zhang, Rishabh Tiwari +8
Progress on training and architecture strategies has enabled LLMs with millions of tokens in context length. However, empirical evidence suggests that such long-context LLMs can co…
The Art of Scaling Reinforcement Learning Compute for LLMs
Devvrit Khatri, Lovish Madaan, Rishabh Tiwari +6
Reinforcement learning (RL) has become central to training large language models (LLMs), yet the field lacks predictive scaling methodologies comparable to those established for pr…
Rethinking Thinking Tokens: LLMs as Improvement Operators
Lovish Madaan, Aniket Didolkar, Suchin Gururangan +6
Reasoning training incentivizes LLMs to produce long chains of thought (long CoT), which among other things, allows them to explore solution strategies with self-checking. This res…
Beyond Verifiable Rewards: Scaling Reinforcement Learning for Language Models to Unverifiable Data
Yunhao Tang, Sid Wang, Lovish Madaan +1
We propose to scale RL to unverifiable data with a novel algorithm JEPO (Jensen's Evidence lower bound Policy Optimization). While most prior efforts on scaling RL for LLMs focus o…
HARP: A challenging human-annotated math reasoning benchmark
Albert S. Yue, Lovish Madaan, Ted Moskovitz +2
Math reasoning is becoming an ever increasing area of focus as we scale large language models. However, even the previously-toughest evals like MATH are now close to saturated by f…
Quantifying Variance in Evaluation Benchmarks
Lovish Madaan, Aaditya K. Singh, Rylan Schaeffer +5
Evaluation benchmarks are the cornerstone of measuring capabilities of large language models (LLMs), as well as driving progress in said capabilities. Originally designed to make c…