Learning Steerable Clarification Policies with Collaborative Self-play
cs.LG
Submitted: 2025-12-03
Updated: 2026-09-13
Comments: COLM 2026
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Resolving Intent Ambiguities by Retrieving Discriminative Clarifying Questions
- Don't lie to your friends: Learning what you know from collaborative self-play
- Reinforced Self-Training (ReST) for Language Modeling
- CTRL: A Conditional Transformer Language Model for Controllable Generation
- Spectrum Tuning: Post-Training for Distributional Coverage and In-Context Steerability
- Training Proactive and Personalized LLM Agents
- Disambiguation in Conversational Question Answering in the Era of LLMs and Agents: A Survey
- Gemma 2: Improving Open Language Models at a Practical Size
- Modeling Future Conversation Turns to Teach LLMs to Ask Clarifying Questions
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks