pith. sign in

All experiments were conducted on 5 NVIDIA H100 80GB GPUs: 1 GPU dedicated to the vLLM server for generation and 4 GPUs for training

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.CL 1

years

2025 1

verdicts

UNVERDICTED 1

representative citing papers

Reasoning about Intent for Ambiguous Requests

cs.CL · 2025-11-13 · unverdicted · novelty 5.0

Reinforcement learning with a dual recall-precision reward trains models to enumerate valid interpretations and answers for ambiguous inputs using only multiple-answer supervision.

citing papers explorer

Showing 1 of 1 citing paper.

  • Reasoning about Intent for Ambiguous Requests cs.CL · 2025-11-13 · unverdicted · none · ref 10

    Reinforcement learning with a dual recall-precision reward trains models to enumerate valid interpretations and answers for ambiguous inputs using only multiple-answer supervision.