paper-with-me

홈 › Papers

Question Asking as Program Generation

2017-11-16 · NeurIPS 2017 12 · Anselm Rothe, Brenden M. Lake, Todd M. Gureckis

A hallmark of human intelligence is the ability to ask rich, creative, and revealing questions. Here we introduce a cognitive model capable of constructing human-like questions. Our approach treats questions as formal programs that, when executed on the state of the world, output an answer. The model specifies a probability distribution over a complex, compositional space of programs, favoring concise programs that help the agent learn in the current context. We evaluate our approach by modeling the types of open-ended questions generated by humans who were attempting to learn about an ambiguous situation in a game. We find that our model predicts what questions people will ask, and can creatively produce novel questions that were not present in the training set. In addition, we compare a number of model variants, finding that both question informativeness and complexity are important for producing human-like questions.

📄 PDF Abstract BibTeX arXiv:1711.06351

Code (1)

anselmrothe/eig

Tasks

Informativeness

Similar Papers 제목 키워드 기반

Modeling question asking using neural program generation

2019-07-23 · Ziyun Wang, Brenden M. Lake

People ask questions that are far richer, more informative, and more creative than current AI systems. We propose a neuro-symbolic framework for modeling human question asking, which represents questions as formal progra…

DecoderQuestion GenerationQuestion-Generationreinforcement-learning+2

Loose LIPS Sink Ships: Asking Questions in Battleship with Language-Informed Program Sampling

2024-02-29 · Gabriel Grand, Valerio Pepe, Jacob Andreas, Joshua B. Tenenbaum

Questions combine our mastery of language with our remarkable facility for reasoning about uncertainty. How do people navigate vast hypothesis spaces to pose informative questions given limited cognitive resources? We st…

Navigate

Curiosity by Design: An LLM-based Coding Assistant Asking Clarification Questions

2025-07-28 · Harsh Darji, Thibaud Lutellier arxiv

Large Language Models (LLMs) are increasingly used as coding assistants. However, the ambiguity of the developer's prompt often leads to incorrect code generation, as current models struggle to infer user intent without …

Prompt EngineeringCode Generation

TreeDiff: AST-Guided Code Generation with Diffusion LLMs

2025-08-02 · Yiming Zeng, Jinghan Cao, Zexin Li, Yiming Chen 외 arxiv

Code generation is increasingly critical for real-world applications. Still, diffusion-based large language models continue to struggle with this demand. Unlike free-form text, code requires syntactic precision; even min…

Code Generation

Asking It All: Generating Contextualized Questions for any Semantic Role

2021-09-10 · EMNLP 2021 11 · Valentina Pyatkin, Paul Roit, Julian Michael, Reut Tsarfaty 외

Asking questions about a situation is an inherent step towards understanding it. To this end, we introduce the task of role question generation, which, given a predicate mention and a passage, requires producing a set of…

AllQuestion GenerationQuestion-Generation