Dialogue Action Tokens: Steering Language Models in Goal-Directed Dialogue with a Multi-Turn Planner

• URL: http://arxiv.org/abs/2406.11978v1
• Date: Mon, 17 Jun 2024 18:01:32 GMT
• Title: Dialogue Action Tokens: Steering Language Models in Goal-Directed Dialogue with a Multi-Turn Planner
• Authors: Kenneth Li, Yiming Wang, Fernanda Viégas, Martin Wattenberg,
• Abstract summary: We present an approach called Dialogue Action Tokens that adapts language model agents to plan goal-directed dialogues. The core idea is to treat each utterance as an action, thereby converting dialogues into games where existing approaches such as reinforcement learning can be applied.
• Score: 51.77263363285369
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We present an approach called Dialogue Action Tokens (DAT) that adapts language model agents to plan goal-directed dialogues. The core idea is to treat each utterance as an action, thereby converting dialogues into games where existing approaches such as reinforcement learning can be applied. Specifically, we freeze a pretrained language model and train a small planner model that predicts a continuous action vector, used for controlled generation in each round. This design avoids the problem of language degradation under reward optimization. When evaluated on the Sotopia platform for social simulations, the DAT-steered LLaMA model surpasses GPT-4's performance. We also apply DAT to steer an attacker language model in a novel multi-turn red-teaming setting, revealing a potential new attack surface.

Related papers

• Plug-and-Play Policy Planner for Large Language Model Powered Dialogue Agents [121.46051697742608]
  We introduce a new dialogue policy planning paradigm to strategize dialogue problems with a tunable language model plug-in named PPDPP. Specifically, we develop a novel training framework to facilitate supervised fine-tuning over available human-annotated data. PPDPP consistently and substantially outperforms existing approaches on three different proactive dialogue applications.
  arXiv  Detail & Related papers  (2023-11-01T03:20:16Z)
• JoTR: A Joint Transformer and Reinforcement Learning Framework for Dialog Policy Learning [53.83063435640911]
  Dialogue policy learning (DPL) is a crucial component of dialogue modelling. We introduce a novel framework, JoTR, to generate flexible dialogue actions. Unlike traditional methods, JoTR formulates a word-level policy that allows for a more dynamic and adaptable dialogue action generation.
  arXiv  Detail & Related papers  (2023-09-01T03:19:53Z)
• FutureTOD: Teaching Future Knowledge to Pre-trained Language Model for Task-Oriented Dialogue [20.79359173822053]
  We propose a novel dialogue pre-training model, FutureTOD, which distills future knowledge to the representation of the previous dialogue context. Our intuition is that a good dialogue representation both learns local context information and predicts future information.
  arXiv  Detail & Related papers  (2023-06-17T10:40:07Z)
• Controllable Mixed-Initiative Dialogue Generation through Prompting [50.03458333265885]
  Mixed-initiative dialogue tasks involve repeated exchanges of information and conversational control. Agents gain control by generating responses that follow particular dialogue intents or strategies, prescribed by a policy planner. Standard approach has been fine-tuning pre-trained language models to perform generation conditioned on these intents. We instead prompt large language models as a drop-in replacement to fine-tuning on conditional generation.
  arXiv  Detail & Related papers  (2023-05-06T23:11:25Z)
• Stabilized In-Context Learning with Pre-trained Language Models for Few Shot Dialogue State Tracking [57.92608483099916]
  Large pre-trained language models (PLMs) have shown impressive unaided performance across many NLP tasks. For more complex tasks such as dialogue state tracking (DST), designing prompts that reliably convey the desired intent is nontrivial. We introduce a saliency model to limit dialogue text length, allowing us to include more exemplars per query.
  arXiv  Detail & Related papers  (2023-02-12T15:05:10Z)
• Post-Training Dialogue Summarization using Pseudo-Paraphrasing [12.083992819138716]
  We propose to post-train pretrained language models (PLMs) to rephrase from dialogue to narratives. Comprehensive experiments show that our approach significantly improves vanilla PLMs on dialogue summarization.
  arXiv  Detail & Related papers  (2022-04-28T13:42:19Z)
• CloneBot: Personalized Dialogue-Response Predictions [0.0]
  The project task was to create a model that, given a speaker ID, chat history, and an utterance query, can predict the response utterance in a conversation. The model is personalized for each speaker. This task can be a useful tool for building speech bots that talk in a human-like manner in a live conversation.
  arXiv  Detail & Related papers  (2021-03-31T01:15:37Z)
• TurnGPT: a Transformer-based Language Model for Predicting Turn-taking in Spoken Dialog [2.2716975311837357]
  We introduce TurnGPT, a transformer-based language model for predicting turn-shifts in spoken dialog. The model has been trained and evaluated on a variety of written and spoken dialog datasets.
  arXiv  Detail & Related papers  (2020-10-21T09:58:39Z)
• 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.