paper-with-me

Papers

Efficient Data Generation for Source-grounded Information-seeking Dialogs: A Use Case for Meeting Transcripts

2024-05-02 · Lotem Golany, Filippo Galgani, Maya Mamo, Nimrod Parasol, Omer Vandsburger, Nadav Bar, Ido Dagan

Automating data generation with Large Language Models (LLMs) has become increasingly popular. In this work, we investigate the feasibility and effectiveness of LLM-based data generation in the challenging setting of source-grounded information-seeking dialogs, with response attribution, over long documents. Our source texts consist of long and noisy meeting transcripts, adding to the task complexity. Since automating attribution remains difficult, we propose a semi-automatic approach: dialog queries and responses are generated with LLMs, followed by human verification and identification of attribution spans. Using this approach, we created MISeD -- Meeting Information Seeking Dialogs dataset -- a dataset of information-seeking dialogs focused on meeting transcripts. Models finetuned with MISeD demonstrate superior performance compared to off-the-shelf models, even those of larger size. Finetuning on MISeD gives comparable response generation quality to finetuning on fully manual data, while improving attribution quality and reducing time and effort.

📄 PDF Abstract BibTeX arXiv:2405.01121

Code (1)

google-research-datasets/mised 공식 구현

Tasks

Response Generation

Similar Papers 제목 키워드 기반

Grounded and Transparent Response Generation for Conversational Information-Seeking Systems

2024-06-27 · Weronika Łajewska

While previous conversational information-seeking (CIS) research has focused on passage retrieval, reranking, and query rewriting, the challenge of synthesizing retrieved information into coherent responses remains. The …

Conversational Response GenerationPassage RetrievalRerankingResponse Generation+1

Evaluating Large Language Models for Document-grounded Response Generation in Information-Seeking Dialogues

2023-09-21 · Norbert Braunschweiler, Rama Doddipatla, Simon Keizer, Svetlana Stoyanchev

In this paper, we investigate the use of large language models (LLMs) like ChatGPT for document-grounded response generation in the context of information-seeking dialogues. For evaluation, we use the MultiDoc2Dial corpu…

Response Generation

HybriDialogue: An Information-Seeking Dialogue Dataset Grounded on Tabular and Textual Data

2021-11-16 · ACL ARR November 2021 11 · Anonymous

A pressing challenge in current dialogue systems is to successfully converse with users on topics with information distributed across different modalities. Previous work in multi-turn dialogue systems has primarily focus…

Response GenerationRetrieval

HybriDialogue: An Information-Seeking Dialogue Dataset Grounded on Tabular and Textual Data

2022-04-28 · Findings (ACL) 2022 5 · Kai Nakamura, Sharon Levy, Yi-Lin Tuan, Wenhu Chen 외

A pressing challenge in current dialogue systems is to successfully converse with users on topics with information distributed across different modalities. Previous work in multiturn dialogue systems has primarily focuse…

Response GenerationRetrieval

Dial HEALTHDIAL for Advice: A Multilingual and Multi-Parallel Spoken Dialogue Dataset for Knowledge-Grounded Information Seeking

2026-05-28 · Songbo Hu, Yinhong Liu, Ej Zhou, Evgeniia Razumovskaia 외 arxiv

Creating spoken dialogue datasets is methodologically challenging, and these challenges are amplified when the goal is to build multilingual, multi-parallel datasets at scale. This work introduces HEALTHDIAL, a large-sca…