paper-with-me

홈 › Papers

Teaching LLMs to Ask: Self-Querying Category-Theoretic Planning for Under-Specified Reasoning

2026-01-27 · Shuhui Qu arxiv

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.

📄 PDF Abstract BibTeX arXiv:2601.20014

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Self-Tuning: Instructing LLMs to Effectively Acquire New Knowledge through Self-Teaching

2024-06-10 · Xiaoying Zhang, Baolin Peng, Ye Tian, Jingyan Zhou 외

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…

Memorization

A Pattern-Hierarchy Classifier for Reduced Teaching

2019-04-16 · Kieran Greer

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…

Clustering

Can LLMs Learn by Teaching for Better Reasoning? A Preliminary Study

2024-06-20 · Xuefei Ning, Zifu Wang, Shiyao Li, Zinan Lin 외

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 Distillation

Understanding Tool-Augmented Agents for Lean Formalization: A Factorial Analysis

2026-04-16 · Ke Zhang, Patricio Gallardo, Maziar Raissi, Sudhir Murthy arxiv

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

2024-09-23 · Haoyu Huang, Tong Niu, Rui Yang, Luping Shi

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