Talk2Ref: A Dataset for Reference Prediction from Scientific Talks

• URL: http://arxiv.org/abs/2510.24478v1
• Date: Tue, 28 Oct 2025 14:50:03 GMT
• Title: Talk2Ref: A Dataset for Reference Prediction from Scientific Talks
• Authors: Frederik Broy, Maike Züfle, Jan Niehues,
• Abstract summary: We introduce Reference Prediction from Talks (RPT), a new task that maps long, and unstructured scientific presentations to relevant papers.<n>We present Talk2Ref, the first large-scale dataset of its kind, containing 6,279 talks and 43,429 cited papers.<n>Our results show that fine-tuning on Talk2Ref significantly improves citation prediction performance.
• Score: 15.95945265244193
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Scientific talks are a growing medium for disseminating research, and automatically identifying relevant literature that grounds or enriches a talk would be highly valuable for researchers and students alike. We introduce Reference Prediction from Talks (RPT), a new task that maps long, and unstructured scientific presentations to relevant papers. To support research on RPT, we present Talk2Ref, the first large-scale dataset of its kind, containing 6,279 talks and 43,429 cited papers (26 per talk on average), where relevance is approximated by the papers cited in the talk's corresponding source publication. We establish strong baselines by evaluating state-of-the-art text embedding models in zero-shot retrieval scenarios, and propose a dual-encoder architecture trained on Talk2Ref. We further explore strategies for handling long transcripts, as well as training for domain adaptation. Our results show that fine-tuning on Talk2Ref significantly improves citation prediction performance, demonstrating both the challenges of the task and the effectiveness of our dataset for learning semantic representations from spoken scientific content. The dataset and trained models are released under an open license to foster future research on integrating spoken scientific communication into citation recommendation systems.

Related papers

• What Should I Cite? A RAG Benchmark for Academic Citation Prediction [24.99107629089983]
  Citation prediction aims to automatically suggest appropriate references, helping scholars navigate the expanding scientific literature.<n>Here we present textbfCiteRAG, the first comprehensive retrieval-augmented generation (RAG)-integrated benchmark for evaluating large language models on academic citation prediction.
  arXiv  Detail & Related papers  (2026-01-21T12:51:47Z)
• On the Role of Context for Discourse Relation Classification in Scientific Writing [10.147545869756867]
  We are interested in the use of discourse-level information to find supporting evidence for AI generated scientific claims.<n>A first step towards this objective is to examine the task of inferring discourse structure in scientific writing.
  arXiv  Detail & Related papers  (2025-10-30T11:05:36Z)
• ScholarCopilot: Training Large Language Models for Academic Writing with Accurate Citations [45.57178343138677]
  We introduce ScholarCopilot, a unified framework designed to enhance existing large language models for academic writing.<n> ScholarCopilot determines when to retrieve scholarly references by generating a retrieval token [RET], which is then used to query a citation database.<n>We jointly optimize both the generation and citation tasks within a single framework to improve efficiency.
  arXiv  Detail & Related papers  (2025-04-01T14:12:14Z)
• Comprehensive Manuscript Assessment with Text Summarization Using 69707 articles [10.943765373420135]
  We harness Scopus to curate a significantly comprehensive and large-scale dataset of information from 69707 scientific articles.<n>We propose a deep learning methodology for the impact-based classification tasks, which leverages semantic features extracted from the manuscripts and paper metadata.
  arXiv  Detail & Related papers  (2025-03-26T07:56:15Z)
• Modeling citation worthiness by using attention-based bidirectional long short-term memory networks and interpretable models [0.0]
  We propose a Bidirectional Long Short-Term Memory (BiLSTM) network with attention mechanism and contextual information to detect sentences that need citations. We produce a new, large dataset (PMOA-CITE) based on PubMed Open Access Subset, which is orders of magnitude larger than previous datasets.
  arXiv  Detail & Related papers  (2024-05-20T17:45:36Z)
• Context-Enhanced Language Models for Generating Multi-Paper Citations [35.80247519023821]
  We propose a method that leverages Large Language Models (LLMs) to generate multi-citation sentences. Our approach involves a single source paper and a collection of target papers, culminating in a coherent paragraph containing multi-sentence citation text.
  arXiv  Detail & Related papers  (2024-04-22T04:30:36Z)
• ILCiteR: Evidence-grounded Interpretable Local Citation Recommendation [31.259805200946175]
  We introduce the evidence-grounded local citation recommendation task, where the target latent space comprises evidence spans for recommending specific papers. Unlike past formulations that simply output recommendations, ILCiteR retrieves ranked lists of evidence span and recommended paper pairs. We contribute a novel dataset for the evidence-grounded local citation recommendation task and demonstrate the efficacy of our proposed conditional neural rank-ensembling approach for re-ranking evidence spans.
  arXiv  Detail & Related papers  (2024-03-13T17:38:05Z)
• Large Language Models as Zero-Shot Conversational Recommenders [52.57230221644014]
  We present empirical studies on conversational recommendation tasks using representative large language models in a zero-shot setting. We construct a new dataset of recommendation-related conversations by scraping a popular discussion website. We observe that even without fine-tuning, large language models can outperform existing fine-tuned conversational recommendation models.
  arXiv  Detail & Related papers  (2023-08-19T15:29:45Z)
• CiteBench: A benchmark for Scientific Citation Text Generation [69.37571393032026]
  CiteBench is a benchmark for citation text generation. We make the code for CiteBench publicly available at https://github.com/UKPLab/citebench.
  arXiv  Detail & Related papers  (2022-12-19T16:10:56Z)
• Tag-Aware Document Representation for Research Paper Recommendation [68.8204255655161]
  We propose a hybrid approach that leverages deep semantic representation of research papers based on social tags assigned by users. The proposed model is effective in recommending research papers even when the rating data is very sparse.
  arXiv  Detail & Related papers  (2022-09-08T09:13:07Z)
• ConvoSumm: Conversation Summarization Benchmark and Improved Abstractive Summarization with Argument Mining [61.82562838486632]
  We crowdsource four new datasets on diverse online conversation forms of news comments, discussion forums, community question answering forums, and email threads. We benchmark state-of-the-art models on our datasets and analyze characteristics associated with the data.
  arXiv  Detail & Related papers  (2021-06-01T22:17:13Z)
• Enhancing Scientific Papers Summarization with Citation Graph [78.65955304229863]
  We redefine the task of scientific papers summarization by utilizing their citation graph. We construct a novel scientific papers summarization dataset Semantic Scholar Network (SSN) which contains 141K research papers in different domains. Our model can achieve competitive performance when compared with the pretrained models.
  arXiv  Detail & Related papers  (2021-04-07T11:13:35Z)
• A Survey on Text Classification: From Shallow to Deep Learning [83.47804123133719]
  The last decade has seen a surge of research in this area due to the unprecedented success of deep learning. This paper fills the gap by reviewing the state-of-the-art approaches from 1961 to 2021. We create a taxonomy for text classification according to the text involved and the models used for feature extraction and classification.
  arXiv  Detail & Related papers  (2020-08-02T00:09:03Z)
• A Hierarchical Network for Abstractive Meeting Summarization with Cross-Domain Pretraining [52.11221075687124]
  We propose a novel abstractive summary network that adapts to the meeting scenario. We design a hierarchical structure to accommodate long meeting transcripts and a role vector to depict the difference among speakers. Our model outperforms previous approaches in both automatic metrics and human evaluation.
  arXiv  Detail & Related papers  (2020-04-04T21:00:41Z)

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.