Broaden your SCOPE! Efficient Multi-turn Conversation Planning for LLMs using Semantic Space

• URL: http://arxiv.org/abs/2503.11586v1
• Date: Fri, 14 Mar 2025 16:55:46 GMT
• Title: Broaden your SCOPE! Efficient Multi-turn Conversation Planning for LLMs using Semantic Space
• Authors: Zhiliang Chen, Xinyuan Niu, Chuan-Sheng Foo, Bryan Kian Hsiang Low,
• Abstract summary: This paper presents a novel approach called Semantic space COnversation Planning with improved Efficiency (SCOPE)<n>SCOPE exploits the dense semantic representation of conversations to perform conversation planning efficiently.<n>As a result, SCOPE can perform conversation planning 70 times faster than conventional simulation-based planning algorithms.
• Score: 40.91931801667421
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models (LLMs) are used in chatbots or AI assistants to hold conversations with a human user. In such applications, the quality (e.g., user engagement, safety) of a conversation is important and can only be exactly known at the end of the conversation. To maximize its expected quality, conversation planning reasons about the stochastic transitions within a conversation to select the optimal LLM response at each turn. Existing simulation-based conversation planning algorithms typically select the optimal response by simulating future conversations with a large number of LLM queries at every turn. However, this process is extremely time-consuming and hence impractical for real-time conversations. This paper presents a novel approach called Semantic space COnversation Planning with improved Efficiency (SCOPE) that exploits the dense semantic representation of conversations to perform conversation planning efficiently. In particular, SCOPE models the stochastic transitions in conversation semantics and their associated rewards to plan entirely within the semantic space. This allows us to select the optimal LLM response at every conversation turn without needing additional LLM queries for simulation. As a result, SCOPE can perform conversation planning 70 times faster than conventional simulation-based planning algorithms when applied to a wide variety of conversation starters and two reward functions seen in the real world, yet achieving a higher reward within a practical planning budget. Our code can be found at: https://github.com/chenzhiliang94/convo-plan-SCOPE.

Related papers

• Efficient Intent-Based Filtering for Multi-Party Conversations Using Knowledge Distillation from LLMs [0.3249879651054463]
  Large language models (LLMs) have showcased remarkable capabilities in conversational AI. These models are resource-intensive, demanding substantial memory and computational power. We propose a cost-effective solution that filters conversational snippets of interest for LLM processing, tailored to the target downstream application.
  arXiv  Detail & Related papers  (2025-03-21T17:34:37Z)
• Beyond the Turn-Based Game: Enabling Real-Time Conversations with Duplex Models [66.24055500785657]
  Traditional turn-based chat systems prevent users from verbally interacting with system while it is generating responses. To overcome these limitations, we adapt existing LLMs to listen users while generating output and provide users with instant feedback. We build a dataset consisting of alternating time slices of queries and responses as well as covering typical feedback types in instantaneous interactions.
  arXiv  Detail & Related papers  (2024-06-22T03:20:10Z)
• Learning to Clarify: Multi-turn Conversations with Action-Based Contrastive Self-Training [33.57497419019826]
  Action-Based Contrastive Self-Training allows for sample-efficient dialogue policy learning in multi-turn conversation. ACT demonstrates substantial conversation modeling improvements over standard approaches to supervised fine-tuning and DPO.
  arXiv  Detail & Related papers  (2024-05-31T22:44:48Z)
• MathChat: Benchmarking Mathematical Reasoning and Instruction Following in Multi-Turn Interactions [58.57255822646756]
  This paper introduces MathChat, a benchmark designed to evaluate large language models (LLMs) across a broader spectrum of mathematical tasks. We evaluate the performance of various SOTA LLMs on the MathChat benchmark, and we observe that while these models excel in single turn question answering, they significantly underperform in more complex scenarios. We develop MathChat sync, a synthetic dialogue based math dataset for LLM finetuning, focusing on improving models' interaction and instruction following capabilities in conversations.
  arXiv  Detail & Related papers  (2024-05-29T18:45:55Z)
• Effective and Efficient Conversation Retrieval for Dialogue State Tracking with Implicit Text Summaries [48.243879779374836]
  Few-shot dialogue state tracking (DST) with Large Language Models (LLM) relies on an effective and efficient conversation retriever to find similar in-context examples for prompt learning. Previous works use raw dialogue context as search keys and queries, and a retriever is fine-tuned with annotated dialogues to achieve superior performance. We handle the task of conversation retrieval based on text summaries of the conversations. A LLM-based conversation summarizer is adopted for query and key generation, which enables effective maximum inner product search.
  arXiv  Detail & Related papers  (2024-02-20T14:31:17Z)
• Generalizing Conversational Dense Retrieval via LLM-Cognition Data Augmentation [25.578440131793858]
  Existing conversational dense retrieval models mostly view a conversation as a fixed sequence of questions and responses. We propose a framework for generalizing Conversational dense retrieval via LLM-cognition data Augmentation (ConvAug) Inspired by human cognition, we devise a cognition-aware process to mitigate the generation of false positives, false negatives, and hallucinations.
  arXiv  Detail & Related papers  (2024-02-11T03:27:22Z)
• 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)
• Recursively Summarizing Enables Long-Term Dialogue Memory in Large Language Models [75.98775135321355]
  Given a long conversation, large language models (LLMs) fail to recall past information and tend to generate inconsistent responses. We propose to generate summaries/ memory using large language models (LLMs) to enhance long-term memory ability.
  arXiv  Detail & Related papers  (2023-08-29T04:59:53Z)

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.