5 papers
Breaking Entropy Bounds: Accelerating RL Training via MTP with Rejection Sampling
Yucheng Li, Huiqiang Jiang, Yang Xu +14
Reinforcement learning (RL) has become a key component in modern large language models, yet the rollout stage remains the key bottleneck in RL training pipelines. Although Multi-To…
Taming Imperfect Process Verifiers: A Sampling Perspective on Backtracking
Dhruv Rohatgi, Abhishek Shetty, Donya Saless +4
Test-time algorithms that combine the generative power of language models with process verifiers that assess the quality of partial generations offer a promising lever for elicitin…
On the Query Complexity of Verifier-Assisted Language Generation
Edoardo Botta, Yuchen Li, Aashay Mehta +3
Recently, a plethora of works have proposed inference-time algorithms (e.g. best-of-n), which incorporate verifiers to assist the generation process. Their quality-efficiency trade…
Promises and Pitfalls of Generative Masked Language Modeling: Theoretical Framework and Practical Guidelines
Yuchen Li, Alexandre Kirchmeyer, Aashay Mehta +5
Autoregressive language models are the currently dominant paradigm for text generation, but they have some fundamental limitations that cannot be remedied by scale-for example inhe…
Transformers are uninterpretable with myopic methods: a case study with bounded Dyck grammars
Kaiyue Wen, Yuchen Li, Bingbin Liu +1
Interpretability methods aim to understand the algorithm implemented by a trained model (e.g., a Transofmer) by examining various aspects of the model, such as the weight matrices…