Towards Zero-Shot, Controllable Dialog Planning with LLMs

• URL: http://arxiv.org/abs/2410.05821v2
• Date: Tue, 04 Mar 2025 16:21:26 GMT
• Title: Towards Zero-Shot, Controllable Dialog Planning with LLMs
• Authors: Dirk Väth, Ngoc Thang Vu,
• Abstract summary: Large Language Models (LLMs) have emerged as an alternative to training task-specific dialog agents.<n>This paper introduces a novel zero-shot method for controllable Conversational Tree Search (CTS) agents.
• Score: 28.392036110582723
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Recently, Large Language Models (LLMs) have emerged as an alternative to training task-specific dialog agents, due to their broad reasoning capabilities and performance in zero-shot learning scenarios. However, many LLM-based dialog systems fall short in planning towards an overarching dialog goal and therefore cannot steer the conversation appropriately. Furthermore, these models struggle with hallucination, making them unsuitable for information access in sensitive domains, such as legal or medical domains, where correctness of information given to users is critical. The recently introduced task Conversational Tree Search (CTS) proposes the use of dialog graphs to avoid hallucination in sensitive domains, however, state-of-the-art agents are Reinforcement Learning (RL) based and require long training times, despite excelling at dialog strategy. This paper introduces a novel zero-shot method for controllable CTS agents, where LLMs guide the dialog planning through domain graphs by searching and pruning relevant graph nodes based on user interaction preferences. We show that these agents significantly outperform state-of-the-art CTS agents ($p<0.0001$; Barnard Exact test) in simulation. This generalizes to all available CTS domains. Finally, we perform user evaluation to test the agent's performance in the wild, showing that our policy significantly ($p<0.05$; Barnard Exact) improves task-success compared to the state-of-the-art RL-based CTS agent.

Related papers

• From Reviews to Dialogues: Active Synthesis for Zero-Shot LLM-based Conversational Recommender System [49.57258257916805]
  Large Language Models (LLMs) demonstrate strong zero-shot recommendation capabilities. Practical applications often favor smaller, internally managed recommender models due to scalability, interpretability, and data privacy constraints. We propose an active data augmentation framework that synthesizes conversational training data by leveraging black-box LLMs guided by active learning techniques.
  arXiv  Detail & Related papers  (2025-04-21T23:05:47Z)
• Evaluating and Enhancing Out-of-Domain Generalization of Task-Oriented Dialog Systems for Task Completion without Turn-level Dialog Annotations [2.453775887722866]
  This work explores whether large language models (LLMs) can be fine-tuned solely on natural language dialogs to perform ToD tasks, without requiring such annotations. We find that models fine-tuned without turn-level annotations generate coherent and contextually appropriate responses. We propose ZeroToD, a framework that incorporates a schema augmentation mechanism to enhance API call accuracy and overall task completion rates.
  arXiv  Detail & Related papers  (2025-02-18T22:10:51Z)
• SWE-Search: Enhancing Software Agents with Monte Carlo Tree Search and Iterative Refinement [18.84439000902905]
  SWE-Search is a multi-agent framework that integrates Monte Carlo Tree Search (MCTS) with a self-improvement mechanism to enhance software agents' performance. This work highlights the potential of self-evaluation driven search techniques to enhance agent reasoning and planning in complex, dynamic software engineering environments.
  arXiv  Detail & Related papers  (2024-10-26T22:45:56Z)
• Agent-as-a-Judge: Evaluate Agents with Agents [61.33974108405561]
  We introduce the Agent-as-a-Judge framework, wherein agentic systems are used to evaluate agentic systems. This is an organic extension of the LLM-as-a-Judge framework, incorporating agentic features that enable intermediate feedback for the entire task-solving process. We present DevAI, a new benchmark of 55 realistic automated AI development tasks.
  arXiv  Detail & Related papers  (2024-10-14T17:57:02Z)
• DS-Agent: Automated Data Science by Empowering Large Language Models with Case-Based Reasoning [56.887047551101574]
  We present DS-Agent, a novel framework that harnesses large language models (LLMs) agent and case-based reasoning (CBR) In the development stage, DS-Agent follows the CBR framework to structure an automatic iteration pipeline, which can flexibly capitalize on the expert knowledge from Kaggle. In the deployment stage, DS-Agent implements a low-resource deployment stage with a simplified CBR paradigm, significantly reducing the demand on foundational capabilities of LLMs.
  arXiv  Detail & Related papers  (2024-02-27T12:26:07Z)
• 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)
• Choice Fusion as Knowledge for Zero-Shot Dialogue State Tracking [5.691339955497443]
  zero-shot dialogue state tracking (DST) tracks user's requirements in task-oriented dialogues without training on desired domains. We propose CoFunDST, which is trained on domain-agnostic QA datasets and directly uses candidate choices of slot-values as knowledge for zero-shot dialogue-state generation. Our proposed model achieves outperformed joint goal accuracy compared to existing zero-shot DST approaches in most domains on the MultiWOZ 2.1.
  arXiv  Detail & Related papers  (2023-02-25T07:32:04Z)
• DiSTRICT: Dialogue State Tracking with Retriever Driven In-Context Tuning [7.5700317050237365]
  We propose DiSTRICT, a generalizable in-context tuning approach for Dialogue State Tracking (DST) DSTRICT retrieves highly relevant training examples for a given dialogue to fine-tune the model without any hand-crafted templates. Experiments with the MultiWOZ benchmark datasets show that DiSTRICT outperforms existing approaches in various zero-shot and few-shot settings.
  arXiv  Detail & Related papers  (2022-12-06T09:40:15Z)
• Credit-cognisant reinforcement learning for multi-agent cooperation [0.0]
  We introduce the concept of credit-cognisant rewards, which allows an agent to perceive the effect its actions had on the environment as well as on its co-agents. We show that by manipulating these experiences and constructing the reward contained within them to include the rewards received by all the agents within the same action sequence, we are able to improve significantly on the performance of independent deep Q-learning.
  arXiv  Detail & Related papers  (2022-11-18T09:00:25Z)
• GODEL: Large-Scale Pre-Training for Goal-Directed Dialog [119.1397031992088]
  We introduce GODEL, a large pre-trained language model for dialog. We show that GODEL outperforms state-of-the-art pre-trained dialog models in few-shot fine-tuning setups. A novel feature of our evaluation methodology is the introduction of a notion of utility that assesses the usefulness of responses.
  arXiv  Detail & Related papers  (2022-06-22T18:19:32Z)
• TASAC: a twin-actor reinforcement learning framework with stochastic policy for batch process control [1.101002667958165]
  Reinforcement Learning (RL) wherein an agent learns the policy by directly interacting with the environment, offers a potential alternative in this context. RL frameworks with actor-critic architecture have recently become popular for controlling systems where state and action spaces are continuous. It has been shown that an ensemble of actor and critic networks further helps the agent learn better policies due to the enhanced exploration due to simultaneous policy learning.
  arXiv  Detail & Related papers  (2022-04-22T13:00:51Z)
• In-Context Learning for Few-Shot Dialogue State Tracking [55.91832381893181]
  We propose an in-context (IC) learning framework for few-shot dialogue state tracking (DST) A large pre-trained language model (LM) takes a test instance and a few annotated examples as input, and directly decodes the dialogue states without any parameter updates. This makes the LM more flexible and scalable compared to prior few-shot DST work when adapting to new domains and scenarios.
  arXiv  Detail & Related papers  (2022-03-16T11:58:24Z)
• Distributed Adaptive Learning Under Communication Constraints [54.22472738551687]
  This work examines adaptive distributed learning strategies designed to operate under communication constraints. We consider a network of agents that must solve an online optimization problem from continual observation of streaming data.
  arXiv  Detail & Related papers  (2021-12-03T19:23:48Z)
• GALAXY: A Generative Pre-trained Model for Task-Oriented Dialog with Semi-Supervised Learning and Explicit Policy Injection [36.77204909711832]
  We propose a novel pre-trained dialog model that explicitly learns dialog policy from limited labeled dialogs and large-scale unlabeled dialog corpora. Specifically, we introduce a dialog act prediction task for policy optimization during pre-training and employ a consistency regularization term to refine the learned representation. Empirical results show that GALAXY substantially improves the performance of task-oriented dialog systems.
  arXiv  Detail & Related papers  (2021-11-29T15:24:36Z)
• Reinforcement Learning for Datacenter Congestion Control [50.225885814524304]
  Successful congestion control algorithms can dramatically improve latency and overall network throughput. Until today, no such learning-based algorithms have shown practical potential in this domain. We devise an RL-based algorithm with the aim of generalizing to different configurations of real-world datacenter networks. We show that this scheme outperforms alternative popular RL approaches, and generalizes to scenarios that were not seen during training.
  arXiv  Detail & Related papers  (2021-02-18T13:49:28Z)
• RADDLE: An Evaluation Benchmark and Analysis Platform for Robust Task-oriented Dialog Systems [75.87418236410296]
  We introduce the RADDLE benchmark, a collection of corpora and tools for evaluating the performance of models across a diverse set of domains. RADDLE is designed to favor and encourage models with a strong generalization ability. We evaluate recent state-of-the-art systems based on pre-training and fine-tuning, and find that grounded pre-training on heterogeneous dialog corpora performs better than training a separate model per domain.
  arXiv  Detail & Related papers  (2020-12-29T08:58:49Z)
• RethinkCWS: Is Chinese Word Segmentation a Solved Task? [81.11161697133095]
  The performance of the Chinese Word (CWS) systems has gradually reached a plateau with the rapid development of deep neural networks. In this paper, we take stock of what we have achieved and rethink what's left in the CWS task.
  arXiv  Detail & Related papers  (2020-11-13T11:07:08Z)
• Predictive Information Accelerates Learning in RL [50.52439807008805]
  We train Soft Actor-Critic (SAC) agents from pixels with an auxiliary task that learns a compressed representation of the predictive information of the RL environment dynamics. We show that PI-SAC agents can substantially improve sample efficiency over challenging baselines on tasks from the DM Control suite of continuous control environments.
  arXiv  Detail & Related papers  (2020-07-24T08:14:41Z)
• Meta Dialogue Policy Learning [58.045067703675095]
  We propose Deep Transferable Q-Network (DTQN) to utilize shareable low-level signals between domains. We decompose the state and action representation space into feature subspaces corresponding to these low-level components. In experiments, our model outperforms baseline models in terms of both success rate and dialogue efficiency.
  arXiv  Detail & Related papers  (2020-06-03T23:53:06Z)

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.