Abstract
BOW, a reinforcement learning framework, enhances language model reasoning by introducing a reasoning bottleneck between the policy and judge models, improving general and next-word reasoning.
Large language models (LLMs) are typically trained via next-word prediction (NWP), which provides strong surface-level fluency but often lacks support for robust reasoning. We propose BOttlenecked next Word exploration (BOW), a novel RL framework that rethinks NWP by introducing a reasoning bottleneck where a policy model first generates a reasoning path rather than predicting the next token directly, after which a frozen judge model predicts the next token distribution based solely on this reasoning path. We train the policy model using GRPO with rewards that quantify how effectively the reasoning path facilitates next-word recovery. Compared with other continual pretraining baselines, we show that BOW improves both the general and next-word reasoning capabilities of the base model, evaluated on various benchmarks. Our findings show that BOW can serve as an effective and scalable alternative to vanilla NWP.
Community
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- Fast Quiet-STaR: Thinking Without Thought Tokens (2025)
- GreenMind: A Next-Generation Vietnamese Large Language Model for Structured and Logical Reasoning (2025)
- Improving LLM First-Token Predictions in Multiple-Choice Question Answering via Prefilling Attack (2025)
- Pretraining Language Models to Ponder in Continuous Space (2025)
- Interleaved Reasoning for Large Language Models via Reinforcement Learning (2025)
- Think Silently, Think Fast: Dynamic Latent Compression of LLM Reasoning Chains (2025)
- Learning to Reason Across Parallel Samples for LLM Reasoning (2025)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment:
@librarian-bot
recommend
Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper
Collections including this paper 0
No Collection including this paper