Zero-dimensional persistent homology on transformer layer hidden states yields three descriptors per layer whose concatenation improves ill-posedness classification and enables topology-conditioned activation steering across three LLMs.
Clam: Selective clarification for ambiguous questions with generative language models
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
LLM-as-an-Investigator improves diagnostic accuracy over direct prompting by using an evidence-first protocol of hypothesis generation, clarification questions, and iterative probability updates in technical problem solving.
GRIL uses stage-specific RL rewards to train LLMs to detect missing premises, pause proactively, and resume grounded reasoning after clarification, yielding up to 45% better premise detection and 30% higher task success on insufficient math datasets.
Introduces NoisyToolBench benchmark and Ask-when-Needed framework to improve LLM tool-use performance when user instructions are unclear or incomplete.
The paper introduces an optimization framework for AI agents to strategically seek support, proving a threshold policy on support value and providing an online algorithm to control missed-support error without distributional assumptions.
A tradeoff model shows generative AI can reduce bias against diverse preferences by strategically eliciting information instead of always inferring from majority patterns.
citing papers explorer
-
The Topology of Ill-Posed Questions: Persistent Homology for Detection and Steering in LLMs
Zero-dimensional persistent homology on transformer layer hidden states yields three descriptors per layer whose concatenation improves ill-posedness classification and enables topology-conditioned activation steering across three LLMs.
-
LLM-as-an-Investigator: Evidence-First Reasoning for Robust Interactive Problem Diagnosis
LLM-as-an-Investigator improves diagnostic accuracy over direct prompting by using an evidence-first protocol of hypothesis generation, clarification questions, and iterative probability updates in technical problem solving.
-
Pause or Fabricate? Training Language Models for Grounded Reasoning
GRIL uses stage-specific RL rewards to train LLMs to detect missing premises, pause proactively, and resume grounded reasoning after clarification, yielding up to 45% better premise detection and 30% higher task success on insufficient math datasets.
-
Learning to Ask: When LLM Agents Meet Unclear Instruction
Introduces NoisyToolBench benchmark and Ask-when-Needed framework to improve LLM tool-use performance when user instructions are unclear or incomplete.
-
Strategic Decision Support for AI Agents
The paper introduces an optimization framework for AI agents to strategically seek support, proving a threshold policy on support value and providing an online algorithm to control missed-support error without distributional assumptions.
-
When to Ask a Question: Understanding Communication Strategies in Generative AI Tools
A tradeoff model shows generative AI can reduce bias against diverse preferences by strategically eliciting information instead of always inferring from majority patterns.
- Alignment has a Fantasia Problem