paper-with-me

Papers

Unified Pragmatic Models for Generating and Following Instructions

2017-11-14 · NAACL 2018 6 · Daniel Fried, Jacob Andreas, Dan Klein

We show that explicit pragmatic inference aids in correctly generating and following natural language instructions for complex, sequential tasks. Our pragmatics-enabled models reason about why speakers produce certain instructions, and about how listeners will react upon hearing them. Like previous pragmatic models, we use learned base listener and speaker models to build a pragmatic speaker that uses the base listener to simulate the interpretation of candidate descriptions, and a pragmatic listener that reasons counterfactually about alternative descriptions. We extend these models to tasks with sequential structure. Evaluation of language generation and interpretation shows that pragmatic inference improves state-of-the-art listener models (at correctly interpreting human instructions) and speaker models (at producing instructions correctly interpreted by humans) in diverse settings.

📄 PDF Abstract BibTeX arXiv:1711.04987

Code (1)

dpfried/pragmatic-instructions 공식 구현

Tasks

Text Generation

Similar Papers 제목 키워드 기반

Pragmatic Instruction Following and Goal Assistance via Cooperative Language-Guided Inverse Planning

2024-02-27 · Tan Zhi-Xuan, Lance Ying, Vikash Mansinghka, Joshua B. Tenenbaum

People often give instructions whose meaning is ambiguous without further context, expecting that their actions or goals will disambiguate their intentions. How can we build assistive agents that follow such instructions…

Bayesian InferenceInstruction Following

SIFToM: Robust Spoken Instruction Following through Theory of Mind

2024-09-17 · Lance Ying, Jason Xinyu Liu, Shivam Aarya, Yizirui Fang 외

Spoken language instructions are ubiquitous in agent collaboration. However, in human-robot collaboration, recognition accuracy for human speech is often influenced by various speech and environmental factors, such as ba…

Instruction FollowingTask Planning

Measuring Pragmatic Influence in Large Language Model Instructions

2026-02-02 · Yilin Geng, Omri Abend, Eduard Hovy, Lea Frermann arxiv

It is not only what we ask large language models (LLMs) to do that matters, but also how we prompt. Phrases like "This is urgent" or "As your supervisor" can shift model behavior without altering task content. We study t…

Instruction Following

Alignment-based compositional semantics for instruction following

2015-08-26 · EMNLP 2015 9 · Jacob Andreas, Dan Klein

This paper describes an alignment-based model for interpreting natural language instructions in context. We approach instruction following as a search over plans, scoring sequences of actions conditioned on structured ob…

Instruction FollowingSentence

Can Large Language Models Understand Real-World Complex Instructions?

2023-09-17 · Qianyu He, Jie Zeng, Wenhao Huang, Lina Chen 외

Large language models (LLMs) can understand human instructions, showing their potential for pragmatic applications beyond traditional NLP tasks. However, they still struggle with complex instructions, which can be either…