1 citations · 2 across the 9 of their papers we have counts for
9 papers
Beyond Repeated Sampling: Learning Search Policies for LLM Reasoning
Ismail Labiad, Matthieu Kowalski, Marc Schoenauer +2
Large language models increasingly tackle hard reasoning problems by spending more test-time compute, yet the dominant strategy remains naive repeated sampling: draw many independe…
Learning through Internalization
Nikolaos Tsilivis, Nirmit Joshi, Marko Medvedev +2
We study internalization processes, by which neural-network-based systems absorb an explicit computational procedure into their own weights, and how they facilitate learning. We in…
Efficient RL Training for LLMs with Experience Replay
Charles Arnal, Vivien Cabannes, Taco Cohen +2
While Experience Replay - the practice of storing rollouts and reusing them multiple times during training - is a foundational technique in general RL, it remains largely unexplore…
Likelihood-Based Reward Designs for General LLM Reasoning
Ariel Kwiatkowski, Natasha Butt, Ismail Labiad +2
Fine-tuning large language models (LLMs) on reasoning benchmarks via reinforcement learning requires a specific reward function, often binary, for each benchmark. This comes with t…
Teaching Models to Teach Themselves: Reasoning at the Edge of Learnability
Shobhita Sundaram, John Quan, Ariel Kwiatkowski +3
RL methods for scaling large reasoning models stall on datasets with low initial success rates, and thus little training signal. We investigate a fundamental question: Can a pretra…
Embedding Trust: Semantic Isotropy Predicts Nonfactuality in Long-Form Text Generation
Dhrupad Bhardwaj, Julia Kempe, Tim G. J. Rudner
To deploy large language models (LLMs) in high-stakes application domains that require substantively accurate responses to open-ended prompts, we need reliable, computationally ine…
Soft Tokens, Hard Truths
Natasha Butt, Ariel Kwiatkowski, Ismail Labiad +2
The use of continuous instead of discrete tokens during the Chain-of-Thought (CoT) phase of reasoning LLMs has garnered attention recently, based on the intuition that a continuous…
Outcome-based Exploration for LLM Reasoning
Yuda Song, Julia Kempe, Remi Munos
Reinforcement learning (RL) has emerged as a powerful method for improving the reasoning abilities of large language models (LLMs). Outcome-based RL, which rewards policies solely…
Tuning without Peeking: Provable Generalization Bounds and Robust LLM Post-Training
Ismail Labiad, Mathurin Videau, Matthieu Kowalski +4
Gradient-based optimization is the workhorse of deep learning, offering efficient and scalable training via backpropagation. However, exposing gradients during training can leak se…