Talks.cam will close on 1 July 2026, further information is available on the UIS Help Site
 

University of Cambridge > Talks.cam > Language Technology Lab Seminars > Implicit Chain-of-Thought: Internalizing Reasoning in Language Models

Implicit Chain-of-Thought: Internalizing Reasoning in Language Models

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Lucas Resck.

Abstract: When leveraging language models for reasoning tasks, generating explicit chain-of-thought (CoT) steps is often crucial for high accuracy. In this work, drawing inspiration from how the human brain transitions from explicit, conscious, deliberate reasoning (System 2) to implicit, automatic, intuitive thinking (System 1), we seek to internalize explicit CoT reasoning within a model that directly produces the final answer, which we define as the implicit CoT paradigm.

To realize implicit CoT, we found a simple yet effective method: starting with a model trained for explicit CoT reasoning, we gradually remove the intermediate steps and finetune the model. This approach enables a finetuned GPT -2 Small model to solve 20-by-20 multiplication with up to 99.5% accuracy, whereas standard training cannot solve beyond 4-by-4 multiplication.

You can try our demo at https://huggingface.co/spaces/yuntian-deng/gpt2-multiplication —-

Bio: Yuntian Deng is an assistant professor at the University of Waterloo and a visiting professor at NVIDIA under Prof. Yejin Choi. He was previously a postdoc at AI2 , also advised by Prof. Choi. He received his PhD from Harvard University under Prof. Alexander Rush and Prof. Stuart Shieber. His recent works include NeuralOS, Interactive Training, WildChat, and Implicit Chain-of-Thought.

This talk is part of the Language Technology Lab Seminars series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2025 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity