Pith. sign in

REVIEW 5 cited by

UniMS-RAG: A Unified Multi-source Retrieval-Augmented Generation for Personalized Dialogue Systems

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2401.13256 v3 pith:C7S7UDJU submitted 2024-01-24 cs.CL cs.AI

classification cs.CLcs.AI
keywords generationresponsetokensdialogueknowledgepersonalizedlanguagerelevance
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Large Language Models (LLMs) has shown exceptional capabilities in many natual language understanding and generation tasks. However, the personalization issue still remains a much-coveted property, especially when it comes to the multiple sources involved in the dialogue system. To better plan and incorporate the use of multiple sources in generating personalized response, we firstly decompose it into three sub-tasks: Knowledge Source Selection, Knowledge Retrieval, and Response Generation. We then propose a novel Unified Multi-Source Retrieval-Augmented Generation system (UniMS-RAG) Specifically, we unify these three sub-tasks with different formulations into the same sequence-to-sequence paradigm during the training, to adaptively retrieve evidences and evaluate the relevance on-demand using special tokens, called acting tokens and evaluation tokens. Enabling language models to generate acting tokens facilitates interaction with various knowledge sources, allowing them to adapt their behavior to diverse task requirements. Meanwhile, evaluation tokens gauge the relevance score between the dialogue context and the retrieved evidence. In addition, we carefully design a self-refinement mechanism to iteratively refine the generated response considering 1) the consistency scores between the generated response and retrieved evidence; and 2) the relevance scores. Experiments on two personalized datasets (DuLeMon and KBP) show that UniMS-RAG achieves state-of-the-art performance on the knowledge source selection and response generation task with itself as a retriever in a unified manner. Extensive analyses and discussions are provided for shedding some new perspectives for personalized dialogue systems.

Discussion (0). Sign in to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Constructing and Evaluating Declarative RAG Pipelines in PyTerrier

    cs.IR 2025-06 conditional novelty 6.0 of 10

    PyTerrier-RAG extends PyTerrier with datatypes, readers, datasets, and metrics for building and evaluating declarative retrieval-augmented generation pipelines.

  2. PersonaLens: A Benchmark for Personalization Evaluation in Conversational AI Assistants

    cs.CL 2025-06 conditional novelty 6.0 of 10

    PersonaLens uses LLM-simulated users and an LLM judge to evaluate personalization in task-oriented conversational assistants across 111 tasks and 20 domains.

  3. Benchmarking and Learning Real-World Customer Service Dialogue

    cs.CL 2025-10 conditional novelty 5.0 of 10

    OlaMind, a Learn-to-Think plus basic-to-hard RL pipeline for RAG customer service, reports +28.92% issue resolution, -6.08% human transfer online, and an 8.6% offline hallucination rate.

  4. GenFlow: Interactive Modular System for Image Generation

    cs.CV 2025-06 conditional novelty 4.0 of 10

    GenFlow combines a node-based editor, retrieval-augmented workflow search, and web-exploration agents to simplify Stable Diffusion image-generation workflows, with a small user study reporting reduced task times and p...

  5. Federated Retrieval-Augmented Generation: A Systematic Mapping Study

    cs.CL 2025-05 reject novelty 4.0 of 10

    A systematic mapping study that classifies 18 federated RAG papers into a taxonomy and highlights evaluation gaps, though its search protocol is not reproducible.

Pith tools