---
title: Answer Convergence Early Stopping
emoji: 🛑
colorFrom: indigo
colorTo: red
sdk: gradio
sdk_version: 5.9.0
app_file: app.py
pinned: false
license: mit
short_description: Demo for EMNLP Paper "Answer Convergence as a Signal..."
---

# 🛑 Answer Convergence as a Signal for Early Stopping in Reasoning

### [EMNLP Accepted] | [Paper (arXiv)](https://arxiv.org/abs/2506.02536) | [GitHub Code](https://github.com/launchnlp/reasoning_earlystop)

**Authors:** Xin Liu, Lu Wang (University of Michigan)

---

## 💡 What is this?
This Space demonstrates the core concept of our paper: **Large Language Models often internally converge on an answer long before they finish generating the full reasoning chain.**

By detecting this **Answer Convergence**, we can stop the generation early, saving **40%+** of inference costs without sacrificing accuracy.

## 🚀 Key Methods
We propose three strategies to detect this signal:
1.  **Answer Consistency:** Unsupervised method checking if the answer stabilizes across reasoning chunks.
2.  **Think Token Adjustment:** Encouraging the model to output the stop signal earlier.
3.  **Learn-to-Stop:** A lightweight supervised module trained on internal activations.