1 citations · 2 across the 9 of their papers we have counts for
4 papers · 1 filter
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…
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…
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…