Search Results for author:
Found 4 papers, 3 papers with code
Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning
To alleviate the long-existing difficulties brought by sparse rewards in RL, which are even exacerbated by the partial correctness of the long chain of thought for reasoning tasks, we further apply a token-level reward model to sample important tokens in reasoning trajectories for learning.
Training Language Models to Critique With Multi-agent Feedback
To overcome these challenges, this paper proposes a novel data generation pipeline, named MultiCritique, that improves the critique ability of LLMs by utilizing multi-agent feedback in both the SFT and reinforcement learning (RL) stages.
InternLM2 Technical Report
The evolution of Large Language Models (LLMs) like ChatGPT and GPT-4 has sparked discussions on the advent of Artificial General Intelligence (AGI).
Ranked #5 on
Long-Context Understanding
on Ada-LEval (BestAnswer)
InternLM-Math: Open Math Large Language Models Toward Verifiable Reasoning
We further explore how to use LEAN to solve math problems and study its performance under the setting of multi-task learning which shows the possibility of using LEAN as a unified platform for solving and proving in math.
