IntentRL-Ambig-CoQA-4B

IntentRL-Ambig-CoQA-4B

This model is trained to handle ambiguous conversational questions by explicitly reasoning about user intent and producing multiple interpretation–answer pairs rather than silently committing to a single interpretation.

It is based on Qwen/Qwen3-4B-Instruct-2507, fine-tuned with RL (DAPO) using a custom reward that encourages recall (covering more valid interpretations) for ambiguous questions and precision for unambiguous ones.

Example

Given a passage and conversational context:

Hilary Duff says her new album is ... "a lot heavier and a lot darker" because of the separation from her husband, Mike Comrie. Duff married Comrie ... in 2010 after dating for three years. Their son, Luca, was born in 2012...

• How long were they married before they had a child? — 2 years
• What is his name?

The model produces multiple interpretation–answer pairs:

1. The question refers to the husband's name → His name is Mike Comrie.
2. The question refers to the son's name → His name is Luca.

Paper

Reasoning about Intent for Ambiguous Requests

Authors: Irina Saparina, Mirella Lapata

Training Details

• Base model: Qwen3-4B-Instruct-2507
• Method: RL with DAPO and a custom recall/precision reward
• Training data: Abg-CoQA conversational QA benchmark
• Ambiguous examples are upsampled to balance training

Code

Training and evaluation code: https://github.com/saparina/intentRL

Citation

@misc{saparina2025reasoningintentambiguousrequests,
      title={Reasoning about Intent for Ambiguous Requests},
      author={Irina Saparina and Mirella Lapata},
      year={2025},
      eprint={2511.10453},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2511.10453},
}