What are they talking about? Benchmarking Large Language Models for Knowledge-Grounded Discussion Summarization

• URL: http://arxiv.org/abs/2505.12474v1
• Date: Sun, 18 May 2025 15:52:24 GMT
• Title: What are they talking about? Benchmarking Large Language Models for Knowledge-Grounded Discussion Summarization
• Authors: Weixiao Zhou, Junnan Zhu, Gengyao Li, Xianfu Cheng, Xinnian Liang, Feifei Zhai, Zhoujun Li,
• Abstract summary: This work aims to address the limitation of outside observer confusion in existing dialogue summarization systems.<n>We model the task output as background and opinion summaries and define two standardized summarization patterns.<n>We evaluate 12 LLMs under structured-prompt and self-reflection paradigms.
• Score: 19.616500850017363
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In this work, we investigate the performance of LLMs on a new task that requires combining discussion with background knowledge for summarization. This aims to address the limitation of outside observer confusion in existing dialogue summarization systems due to their reliance solely on discussion information. To achieve this, we model the task output as background and opinion summaries and define two standardized summarization patterns. To support assessment, we introduce the first benchmark comprising high-quality samples consistently annotated by human experts and propose a novel hierarchical evaluation framework with fine-grained, interpretable metrics. We evaluate 12 LLMs under structured-prompt and self-reflection paradigms. Our findings reveal: (1) LLMs struggle with background summary retrieval, generation, and opinion summary integration. (2) Even top LLMs achieve less than 69% average performance across both patterns. (3) Current LLMs lack adequate self-evaluation and self-correction capabilities for this task.

Related papers

• Improving Multilingual Retrieval-Augmented Language Models through Dialectic Reasoning Argumentations [65.11348389219887]
  We introduce Dialectic-RAG (DRAG), a modular approach that evaluates retrieved information by comparing, contrasting, and resolving conflicting perspectives.<n>We show the impact of our framework both as an in-context learning strategy and for constructing demonstrations to instruct smaller models.
  arXiv  Detail & Related papers  (2025-04-07T06:55:15Z)
• Contextualizing Search Queries In-Context Learning for Conversational Rewriting with LLMs [0.0]
  This paper introduces Prompt-Guided In-Context Learning, a novel approach for few-shot conversational query rewriting.<n>Our method employs carefully designed prompts, incorporating task descriptions, input/output format specifications, and a small set of illustrative examples.<n>Experiments on benchmark datasets, TREC and Taskmaster-1, demonstrate that our approach significantly outperforms strong baselines.
  arXiv  Detail & Related papers  (2025-02-20T20:02:42Z)
• LLM-as-an-Interviewer: Beyond Static Testing Through Dynamic LLM Evaluation [24.103034843158717]
  We introduce LLM-as-an-Interviewer, a novel paradigm for evaluating large language models (LLMs)<n>This approach leverages multi-turn interactions where the interviewer actively provides feedback on responses and poses follow-up questions to the evaluated LLM.<n>We apply the framework to evaluate six models on the MATH and DepthQA tasks.
  arXiv  Detail & Related papers  (2024-12-10T15:00:32Z)
• Increasing faithfulness in human-human dialog summarization with Spoken Language Understanding tasks [0.0]
  We propose an exploration of how incorporating task-related information can enhance the summarization process. Results show that integrating models with task-related information improves summary accuracy, even with varying word error rates.
  arXiv  Detail & Related papers  (2024-09-16T08:15:35Z)
• CADS: A Systematic Literature Review on the Challenges of Abstractive Dialogue Summarization [7.234196390284036]
  This article summarizes the research on Transformer-based abstractive summarization for English dialogues.<n>We cover the main challenges present in dialog summarization (i.e., language, structure, comprehension, speaker, salience, and factuality)<n>We find that while some challenges, like language, have seen considerable progress, others, such as comprehension, factuality, and salience, remain difficult and hold significant research opportunities.
  arXiv  Detail & Related papers  (2024-06-11T17:30:22Z)
• FENICE: Factuality Evaluation of summarization based on Natural language Inference and Claim Extraction [85.26780391682894]
  We propose Factuality Evaluation of summarization based on Natural language Inference and Claim Extraction (FENICE) FENICE leverages an NLI-based alignment between information in the source document and a set of atomic facts, referred to as claims, extracted from the summary. Our metric sets a new state of the art on AGGREFACT, the de-facto benchmark for factuality evaluation.
  arXiv  Detail & Related papers  (2024-03-04T17:57:18Z)
• Investigating Consistency in Query-Based Meeting Summarization: A Comparative Study of Different Embedding Methods [0.0]
  Text Summarization is one of famous applications in Natural Language Processing (NLP) field. It aims to automatically generate summary with important information based on a given context. In this paper, we are inspired by "QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarization" proposed by Microsoft. We also propose our Locater model designed to extract relevant spans based on given transcript and query, which are then summarized by Summarizer model.
  arXiv  Detail & Related papers  (2024-02-10T08:25:30Z)
• Benchmarking Generation and Evaluation Capabilities of Large Language Models for Instruction Controllable Summarization [132.25202059478065]
  We benchmark large language models (LLMs) on instruction controllable text summarization. Our study reveals that instruction controllable text summarization remains a challenging task for LLMs.
  arXiv  Detail & Related papers  (2023-11-15T18:25:26Z)
• Measuring and Improving Chain-of-Thought Reasoning in Vision-Language Models [61.28463542324576]
  Vision-language models (VLMs) have recently demonstrated strong efficacy as visual assistants that can generate human-like outputs. We evaluate existing state-of-the-art VLMs and find that even the best-performing model is unable to demonstrate strong visual reasoning capabilities and consistency. We propose a two-stage training framework aimed at improving both the reasoning performance and consistency of VLMs.
  arXiv  Detail & Related papers  (2023-09-08T17:49:44Z)
• Improving Open Information Extraction with Large Language Models: A Study on Demonstration Uncertainty [52.72790059506241]
  Open Information Extraction (OIE) task aims at extracting structured facts from unstructured text. Despite the potential of large language models (LLMs) like ChatGPT as a general task solver, they lag behind state-of-the-art (supervised) methods in OIE tasks.
  arXiv  Detail & Related papers  (2023-09-07T01:35:24Z)
• On Learning to Summarize with Large Language Models as References [101.79795027550959]
  Large language models (LLMs) are favored by human annotators over the original reference summaries in commonly used summarization datasets. We study an LLM-as-reference learning setting for smaller text summarization models to investigate whether their performance can be substantially improved.
  arXiv  Detail & Related papers  (2023-05-23T16:56:04Z)
• Robust Saliency-Aware Distillation for Few-shot Fine-grained Visual Recognition [57.08108545219043]
  Recognizing novel sub-categories with scarce samples is an essential and challenging research topic in computer vision. Existing literature addresses this challenge by employing local-based representation approaches. This article proposes a novel model, Robust Saliency-aware Distillation (RSaD), for few-shot fine-grained visual recognition.
  arXiv  Detail & Related papers  (2023-05-12T00:13:17Z)
• Benchmarking Large Language Models for News Summarization [79.37850439866938]
  Large language models (LLMs) have shown promise for automatic summarization but the reasons behind their successes are poorly understood. We find instruction tuning, and not model size, is the key to the LLM's zero-shot summarization capability.
  arXiv  Detail & Related papers  (2023-01-31T18:46:19Z)
• SWING: Balancing Coverage and Faithfulness for Dialogue Summarization [67.76393867114923]
  We propose to utilize natural language inference (NLI) models to improve coverage while avoiding factual inconsistencies. We use NLI to compute fine-grained training signals to encourage the model to generate content in the reference summaries that have not been covered. Experiments on the DialogSum and SAMSum datasets confirm the effectiveness of the proposed approach.
  arXiv  Detail & Related papers  (2023-01-25T09:33:11Z)
• Author Clustering and Topic Estimation for Short Texts [69.54017251622211]
  We propose a novel model that expands on the Latent Dirichlet Allocation by modeling strong dependence among the words in the same document. We also simultaneously cluster users, removing the need for post-hoc cluster estimation. Our method performs as well as -- or better -- than traditional approaches to problems arising in short text.
  arXiv  Detail & Related papers  (2021-06-15T20:55:55Z)
• Reference Knowledgeable Network for Machine Reading Comprehension [43.352833140317486]
  Multi-choice Machine Reading (MRC) is a major and challenging form of MRC tasks. We propose a novel reference-based knowledge enhancement model based on span extraction called Reference Knowledgeable Network (RekNet) In detail, RekNet refines fine-grained critical information and defines it as Reference Span, then quotes external knowledge quadruples by the co-occurrence information of Reference Span and answer options.
  arXiv  Detail & Related papers  (2020-12-07T14:11:33Z)
• 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.