1 citations · 1 across the 7 of their papers we have counts for
8 papers
Trust the Critic More
Kaiyue Wen, Luke Bailey, Arvind Mahankali +1
Standard language model RL algorithms credit every token of a long rollout with the same advantage determined by the terminal reward. Actor-critic methods can provide finer-grained…
Pseudo-Formalization for Automatic Proof Verification
Slim Barkallah, Luke Bailey, Kaiyue Wen +2
Reliable verification of proofs remains a bottleneck for training and evaluating AI systems on hard mathematical reasoning. Fully formal proofs, in languages like Lean, are easy to…
Scaling Self-Play with Self-Guidance
Luke Bailey, Kaiyue Wen, Kefan Dong +2
LLM self-play algorithms are notable in that, in principle, nothing bounds their learning: a Conjecturer model creates problems for a Solver, and both improve together. However, in…
QuestA: Expanding Reasoning Capacity in LLMs via Question Augmentation
Jiazheng Li, Hongzhou Lin, Hong Lu +5
Reinforcement learning (RL) has emerged as a central paradigm for training large language models (LLMs) in reasoning tasks. Yet recent studies question RL's ability to incentivize…
Task Generalization With AutoRegressive Compositional Structure: Can Learning From Tasks Generalize to Tasks?
Amirhesam Abedsoltan, Huaqing Zhang, Kaiyue Wen +3
Large language models (LLMs) exhibit remarkable task generalization, solving tasks they were never explicitly trained on with only a few demonstrations. This raises a fundamental q…
From Sparse Dependence to Sparse Attention: Unveiling How Chain-of-Thought Enhances Transformer Sample Efficiency
Kaiyue Wen, Huaqing Zhang, Hongzhou Lin +1
Chain-of-thought (CoT) significantly enhances the reasoning performance of large language models (LLM). While current theoretical studies often attribute this improvement to increa…
RNNs are not Transformers (Yet): The Key Bottleneck on In-context Retrieval
Kaiyue Wen, Xingyu Dang, Kaifeng Lyu
This paper investigates the gap in representation powers of Recurrent Neural Networks (RNNs) and Transformers in the context of solving algorithmic problems. We focus on understand…
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…