Teaching LLMs to Ask: Self-Querying Category-Theoretic Planning for Under-Specified Reasoning
Inference-time planning with large language models frequently breaks under partial observability: when task-critical preconditions are not specified at query time, models tend to hallucinate missing facts or produce plans that violate hard constraints. We introduce \textbf{Self-Querying Bidirectional Categorical Planning (SQ-BCP)}, which explicitly represents precondition status (\texttt{Sat}/\texttt{Viol}/\texttt{Unk}) and resolves unknowns via (i) targeted self-queries to an oracle/user or (ii) \emph{bridging} hypotheses that establish the missing condition through an additional action. SQ-BCP performs bidirectional search and invokes a pullback-based verifier as a categorical certificate of goal compatibility, while using distance-based scores only for ranking and pruning. We prove that when the verifier succeeds and hard constraints pass deterministic checks, accepted plans are compatible with goal requirements; under bounded branching and finite resolution depth, SQ-BCP finds an accepting plan when one exists. Across WikiHow and RecipeNLG tasks with withheld preconditions, SQ-BCP reduces resource-violation rates to \textbf{14.9\%} and \textbf{5.8\%} (vs.\ \textbf{26.0\%} and \textbf{15.7\%} for the best baseline), while maintaining competitive reference quality.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Self-Tuning: Instructing LLMs to Effectively Acquire New Knowledge through Self-Teaching
Large language models (LLMs) often struggle to provide up-to-date information due to their one-time training and the constantly evolving nature of the world. To keep LLMs current, existing approaches typically involve co…
MemorizationA Pattern-Hierarchy Classifier for Reduced Teaching
This paper describes a design that can be used for Explainable AI. The lower level is a nested ensemble of patterns created by self-organisation. The upper level is a hierarchical tree, where nodes are linked through ind…
ClusteringCan LLMs Learn by Teaching for Better Reasoning? A Preliminary Study
Teaching to improve student models (e.g., knowledge distillation) is an extensively studied methodology in LLMs. However, for humans, teaching improves not only students but also teachers, by fostering more rigorous and …
In-Context LearningKnowledge DistillationUnderstanding Tool-Augmented Agents for Lean Formalization: A Factorial Analysis
Automatic translation of natural language mathematics into faithful Lean 4 code is hindered by the fundamental dissonance between informal set-theoretic intuition and strict formal type theory. This gap often causes LLMs…
RAM2C: A Liberal Arts Educational Chatbot based on Retrieval-augmented Multi-role Multi-expert Collaboration
Recently, many studies focus on utilizing large language models (LLMs) into educational dialogues. Especially, within liberal arts dialogues, educators must balance \textbf{H}umanized communication, \textbf{T}eaching exp…
ChatbotEthicsRetrieval