paper-with-me

홈 › Papers

Successfully Guiding Humans with Imperfect Instructions by Highlighting Potential Errors and Suggesting Corrections

2024-02-26 · Lingjun Zhao, Khanh Nguyen, Hal Daumé III

Language models will inevitably err in situations with which they are unfamiliar. However, by effectively communicating uncertainties, they can still guide humans toward making sound decisions in those contexts. We demonstrate this idea by developing HEAR, a system that can successfully guide humans in simulated residential environments despite generating potentially inaccurate instructions. Diverging from systems that provide users with only the instructions they generate, HEAR warns users of potential errors in its instructions and suggests corrections. This rich uncertainty information effectively prevents misguidance and reduces the search space for users. Evaluation with 80 users shows that HEAR achieves a 13% increase in success rate and a 29% reduction in final location error distance compared to only presenting instructions to users. Interestingly, we find that offering users possibilities to explore, HEAR motivates them to make more attempts at the task, ultimately leading to a higher success rate. To our best knowledge, this work is the first to show the practical benefits of uncertainty communication in a long-horizon sequential decision-making problem.

📄 PDF Abstract BibTeX arXiv:2402.16973

Code (0)

등록된 구현이 없습니다.

Tasks

Decision MakingSequential Decision Making

Similar Papers 제목 키워드 기반

CoLa -- Learning to Interactively Collaborate with Large LMs

2025-04-03 · Abhishek Sharma, Dan Goldwasser

LLMs' remarkable ability to tackle a wide range of language tasks opened new opportunities for collaborative human-AI problem solving. LLMs can amplify human capabilities by applying their intuitions and reasoning strate…

CoLAText Generation

Most Important Fundamental Rule of Poker Strategy

2019-06-08 · Sam Ganzfried, Max Chiswick

Poker is a large complex game of imperfect information, which has been singled out as a major AI challenge problem. Recently there has been a series of breakthroughs culminating in agents that have successfully defeated …

Game of Poker

Learning from Imperfect Demonstrations via Temporal Behavior Tree-Guided Trajectory Repair

2026-04-05 · Aniruddh G. Puranic, Sebastian Schirmer, John S. Baras, Calin Belta arxiv

Learning robot control policies from demonstrations is a powerful paradigm, yet real-world data is often suboptimal, noisy, or otherwise imperfect, posing significant challenges for imitation and reinforcement learning. …

Reinforcement Learning

Plan-Grounded Large Language Models for Dual Goal Conversational Settings

2024-02-01 · Diogo Glória-Silva, Rafael Ferreira, Diogo Tavares, David Semedo 외

Training Large Language Models (LLMs) to follow user instructions has been shown to supply the LLM with ample capacity to converse fluently while being aligned with humans. Yet, it is not completely clear how an LLM can …

Guiding Policies with Language via Meta-Learning

2018-11-19 · ICLR 2019 5 · John D. Co-Reyes, Abhishek Gupta, Suvansh Sanjeev, Nick Altieri 외

Behavioral skills or policies for autonomous agents are conventionally learned from reward functions, via reinforcement learning, or from demonstrations, via imitation learning. However, both modes of task specification …

Imitation LearningInstruction FollowingMeta-LearningReinforcement Learning