CoMAC: Conversational Agent for Multi-Source Auxiliary Context with Sparse and Symmetric Latent Interactions

• URL: http://arxiv.org/abs/2503.19274v1
• Date: Tue, 25 Mar 2025 02:09:52 GMT
• Title: CoMAC: Conversational Agent for Multi-Source Auxiliary Context with Sparse and Symmetric Latent Interactions
• Authors: Junfeng Liu, Christopher T. Symons, Ranga Raju Vatsavai,
• Abstract summary: This paper introduces a novel method, Conversational Auxiliary Agent for Multi-Source Context with Sparse and Symmetric Latent Interactions (CoMAC)<n>CoMAC employs specialized encoding streams and post-fusion grounding networks for multiple data sources to identify relevant persona and knowledge information for the conversation.<n>Our experiments show that CoMAC improves the relevant persona and knowledge prediction accuracies and response generation quality significantly over two state-of-the-art methods.
• Score: 4.100095195067256
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Recent advancements in AI-driven conversational agents have exhibited immense potential of AI applications. Effective response generation is crucial to the success of these agents. While extensive research has focused on leveraging multiple auxiliary data sources (e.g., knowledge bases and personas) to enhance response generation, existing methods often struggle to efficiently extract relevant information from these sources. There are still clear limitations in the ability to combine versatile conversational capabilities with adherence to known facts and adaptation to large variations in user preferences and belief systems, which continues to hinder the wide adoption of conversational AI tools. This paper introduces a novel method, Conversational Agent for Multi-Source Auxiliary Context with Sparse and Symmetric Latent Interactions (CoMAC), for conversation generation, which employs specialized encoding streams and post-fusion grounding networks for multiple data sources to identify relevant persona and knowledge information for the conversation. CoMAC also leverages a novel text similarity metric that allows bi-directional information sharing among multiple sources and focuses on a selective subset of meaningful words. Our experiments show that CoMAC improves the relevant persona and knowledge prediction accuracies and response generation quality significantly over two state-of-the-art methods.

Related papers

• A Desideratum for Conversational Agents: Capabilities, Challenges, and Future Directions [51.96890647837277]
  Large Language Models (LLMs) have propelled conversational AI from traditional dialogue systems into sophisticated agents capable of autonomous actions, contextual awareness, and multi-turn interactions with users. This survey paper presents a desideratum for next-generation Conversational Agents - what has been achieved, what challenges persist, and what must be done for more scalable systems that approach human-level intelligence.
  arXiv  Detail & Related papers  (2025-04-07T21:01:25Z)
• Toward Agentic AI: Generative Information Retrieval Inspired Intelligent Communications and Networking [87.82985288731489]
  Agentic AI has emerged as a key paradigm for intelligent communications and networking.<n>This article emphasizes the role of knowledge acquisition, processing, and retrieval in agentic AI for telecom systems.
  arXiv  Detail & Related papers  (2025-02-24T06:02:25Z)
• Multi-granular Training Strategies for Robust Multi-hop Reasoning Over Noisy and Heterogeneous Knowledge Sources [0.0]
  Multi-source multi-hop question answering (QA) represents a challenging task in natural language processing.<n>Existing methods often suffer from cascading errors, insufficient handling of knowledge conflicts, and computational inefficiency.<n>We propose Adaptive Multi-source Knowledge-Oriented Reasoning (AMKOR) to dynamically fuse parametric and retrieved knowledge.
  arXiv  Detail & Related papers  (2025-02-09T16:06:43Z)
• Context Retrieval via Normalized Contextual Latent Interaction for Conversational Agent [3.9635467316436133]
  We present a novel method, PK-NCLI, that is able to accurately and efficiently identify relevant auxiliary information to improve the quality of conversational responses. Our experimental results indicate that PK-NCLI outperforms the state-of-the-art method, PK-FoCus, in terms of perplexity, knowledge grounding, and training efficiency.
  arXiv  Detail & Related papers  (2023-12-01T18:53:51Z)
• MMoE: Enhancing Multimodal Models with Mixtures of Multimodal Interaction Experts [92.76662894585809]
  We introduce an approach to enhance multimodal models, which we call Multimodal Mixtures of Experts (MMoE) MMoE is able to be applied to various types of models to gain improvement.
  arXiv  Detail & Related papers  (2023-11-16T05:31:21Z)
• Persona-Coded Poly-Encoder: Persona-Guided Multi-Stream Conversational Sentence Scoring [4.454629320045368]
  We present a novel Persona-Coded Poly-Encoder method that leverages persona information in a multi-stream encoding scheme to improve the quality of response generation for conversations. Our experimental results and analysis demonstrate that our method can improve conversation quality over the baseline method Poly-Encoder by 3.32% and 2.94% in terms of BLEU score and HR@1.
  arXiv  Detail & Related papers  (2023-09-28T18:07:01Z)
• PICK: Polished & Informed Candidate Scoring for Knowledge-Grounded Dialogue Systems [59.1250765143521]
  Current knowledge-grounded dialogue systems often fail to align the generated responses with human-preferred qualities. We propose Polished & Informed Candidate Scoring (PICK), a generation re-scoring framework. We demonstrate the effectiveness of PICK in generating responses that are more faithful while keeping them relevant to the dialogue history.
  arXiv  Detail & Related papers  (2023-09-19T08:27:09Z)
• AutoConv: Automatically Generating Information-seeking Conversations with Large Language Models [74.10293412011455]
  We propose AutoConv for synthetic conversation generation. Specifically, we formulate the conversation generation problem as a language modeling task. We finetune an LLM with a few human conversations to capture the characteristics of the information-seeking process.
  arXiv  Detail & Related papers  (2023-08-12T08:52:40Z)
• INSCIT: Information-Seeking Conversations with Mixed-Initiative Interactions [47.90088587508672]
  InSCIt is a dataset for Information-Seeking Conversations with mixed-initiative Interactions. It contains 4.7K user-agent turns from 805 human-human conversations. We report results of two systems based on state-of-the-art models of conversational knowledge identification and open-domain question answering.
  arXiv  Detail & Related papers  (2022-07-02T06:18:12Z)
• Multi-Stage Conversational Passage Retrieval: An Approach to Fusing Term Importance Estimation and Neural Query Rewriting [56.268862325167575]
  We tackle conversational passage retrieval (ConvPR) with query reformulation integrated into a multi-stage ad-hoc IR system. We propose two conversational query reformulation (CQR) methods: (1) term importance estimation and (2) neural query rewriting. For the former, we expand conversational queries using important terms extracted from the conversational context with frequency-based signals. For the latter, we reformulate conversational queries into natural, standalone, human-understandable queries with a pretrained sequence-tosequence model.
  arXiv  Detail & Related papers  (2020-05-05T14:30:20Z)

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.