Decision-Oriented Dialogue for Human-AI Collaboration

• URL: http://arxiv.org/abs/2305.20076v3
• Date: Sun, 5 May 2024 20:41:13 GMT
• Title: Decision-Oriented Dialogue for Human-AI Collaboration
• Authors: Jessy Lin, Nicholas Tomlin, Jacob Andreas, Jason Eisner,
• Abstract summary: We describe a class of tasks called decision-oriented dialogues, in which AI assistants such as large language models (LMs) must collaborate with one or more humans via natural language to help them make complex decisions. We formalize three domains in which users face everyday decisions: (1) choosing an assignment of reviewers to conference papers, (2) planning a multi-step itinerary in a city, and (3) negotiating travel plans for a group of friends. For each task, we build a dialogue environment where agents receive a reward based on the quality of the final decision they reach.
• Score: 62.367222979251444
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We describe a class of tasks called decision-oriented dialogues, in which AI assistants such as large language models (LMs) must collaborate with one or more humans via natural language to help them make complex decisions. We formalize three domains in which users face everyday decisions: (1) choosing an assignment of reviewers to conference papers, (2) planning a multi-step itinerary in a city, and (3) negotiating travel plans for a group of friends. In each of these settings, AI assistants and users have disparate abilities that they must combine to arrive at the best decision: assistants can access and process large amounts of information, while users have preferences and constraints external to the system. For each task, we build a dialogue environment where agents receive a reward based on the quality of the final decision they reach. We evaluate LMs in self-play and in collaboration with humans and find that they fall short compared to human assistants, achieving much lower rewards despite engaging in longer dialogues. We highlight a number of challenges models face in decision-oriented dialogues, ranging from goal-directed behavior to reasoning and optimization, and release our environments as a testbed for future work.

Related papers

• Interactive Dialogue Agents via Reinforcement Learning on Hindsight Regenerations [58.65755268815283]
  Many real dialogues are interactive, meaning an agent's utterances will influence their conversational partner, elicit information, or change their opinion. We use this fact to rewrite and augment existing suboptimal data, and train via offline reinforcement learning (RL) an agent that outperforms both prompting and learning from unaltered human demonstrations. Our results in a user study with real humans show that our approach greatly outperforms existing state-of-the-art dialogue agents.
  arXiv  Detail & Related papers  (2024-11-07T21:37:51Z)
• Zero-Shot Goal-Directed Dialogue via RL on Imagined Conversations [70.7884839812069]
  Large language models (LLMs) have emerged as powerful and general solutions to many natural language tasks. However, many of the most important applications of language generation are interactive, where an agent has to talk to a person to reach a desired outcome. In this work, we explore a new method for adapting LLMs with RL for such goal-directed dialogue.
  arXiv  Detail & Related papers  (2023-11-09T18:45:16Z)
• ChoiceMates: Supporting Unfamiliar Online Decision-Making with Multi-Agent Conversational Interactions [58.71970923420007]
  We present ChoiceMates, a system that enables conversations with a dynamic set of LLM-powered agents. Agents, as opinionated personas, flexibly join the conversation, not only providing responses but also conversing among themselves to elicit each agent's preferences. Our study (n=36) comparing ChoiceMates to conventional web search and single-agent showed that ChoiceMates was more helpful in discovering, diving deeper, and managing information compared to Web with higher confidence.
  arXiv  Detail & Related papers  (2023-10-02T16:49:39Z)
• Improving Grounded Language Understanding in a Collaborative Environment by Interacting with Agents Through Help Feedback [42.19685958922537]
  We argue that human-AI collaboration should be interactive, with humans monitoring the work of AI agents and providing feedback that the agent can understand and utilize. In this work, we explore these directions using the challenging task defined by the IGLU competition, an interactive grounded language understanding task in a MineCraft-like world.
  arXiv  Detail & Related papers  (2023-04-21T05:37:59Z)
• Human-AI Collaboration in Decision-Making: Beyond Learning to Defer [4.874780144224057]
  Human-AI collaboration (HAIC) in decision-making aims to create synergistic teaming between humans and AI systems. Learning to Defer (L2D) has been presented as a promising framework to determine who among humans and AI should take which decisions. L2D entails several often unfeasible requirements, such as availability of predictions from humans for every instance or ground-truth labels independent from said decision-makers.
  arXiv  Detail & Related papers  (2022-06-27T11:40:55Z)
• KETOD: Knowledge-Enriched Task-Oriented Dialogue [77.59814785157877]
  Existing studies in dialogue system research mostly treat task-oriented dialogue and chit-chat as separate domains. We investigate how task-oriented dialogue and knowledge-grounded chit-chat can be effectively integrated into a single model.
  arXiv  Detail & Related papers  (2022-05-11T16:01:03Z)
• WeaSuL: Weakly Supervised Dialogue Policy Learning: Reward Estimation for Multi-turn Dialogue [17.663449579168297]
  We simulate a dialogue between an agent and a user (modelled similar to an agent with supervised learning objective) to interact with each other. The agent uses dynamic blocking to generate ranked diverse responses and exploration-exploitation to select among the Top-K responses. Empirical studies with two benchmarks indicate that our model can significantly out-perform the response quality and lead to a successful conversation.
  arXiv  Detail & Related papers  (2021-08-01T08:00:45Z)
• Adding Chit-Chat to Enhance Task-Oriented Dialogues [36.93917437554091]
  Chit-Chat can be added to task-oriented dialogues to make virtual assistant conversations more engaging and interactive. We present our new chit-chat-based annotations to 23.8K dialogues from two popular task-oriented dialogue datasets. We also propose three new models for adding chit-chat to task-oriented dialogues, explicitly trained to predict user goals and to generate contextually relevant chit-chat responses.
  arXiv  Detail & Related papers  (2020-10-24T03:22:43Z)
• Distributed Structured Actor-Critic Reinforcement Learning for Universal Dialogue Management [29.57382819573169]
  We focus on devising a policy that chooses which dialogue action to respond to the user. The sequential system decision-making process can be abstracted into a partially observable Markov decision process. In the past few years, there are many deep reinforcement learning (DRL) algorithms, which use neural networks (NN) as function approximators.
  arXiv  Detail & Related papers  (2020-09-22T05:39:31Z)
• TOD-BERT: Pre-trained Natural Language Understanding for Task-Oriented Dialogue [113.45485470103762]
  In this work, we unify nine human-human and multi-turn task-oriented dialogue datasets for language modeling. To better model dialogue behavior during pre-training, we incorporate user and system tokens into the masked language modeling.
  arXiv  Detail & Related papers  (2020-04-15T04:09:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.