Workshop Schedule (UPDATED)

The workshop will take place both in-person (in Lotus Suite 15) and online on August 16th, 2024. at ACL 2024.

The SDP 2024 proceedings are available at this link

Program Time (Local) Details
Intro & Welcome 09:00 - 09:10 Introduction to the 4th Workshop on Scholarly Document Processing (SDP)
Keynote 1 09:10 - 09:50 Speaker: Iryna Gurevych (Technical University Darmstadt and head of the UKP Lab)
Title: How to InterText? Elevating NLP to the cross-document level
Oral Talks 1 09:50 - 10:35 3 talks:
  • Simulating Expert Discussions with Multi-agent for Enhanced Scientific Problem Solving (Ziyue Li, Yuan Chang, Xiaoqiu Le) (in-person)
  • CoSAEmb: Contrastive Section-aware Aspect Embeddings for Scientific Articles (Shruti Singh, Mayank Singh) (in-person)
  • AffilGood: Building reliable institution name disambiguation tools to improve scientific literature analysis (Nicolau Duran-Silva, Pablo Accuosto, Piotr Przybyła, Horacio Saggion) (in-person)
Break 1 + Networking 10:35 - 11:00
Keynote 2 11:00 - 11:40 Speaker: Doug Downey (Northwestern University and Allen Institute for AI, USA)
Title: Chasing high-precision NLP at discount prices: Lessons for accelerating science
Shared Tasks 11:40 - 12:10 2 overview talks:
  • DAGPap24: Detecting Automatically Generated Scientific Papers
  • Context24: Contextualizing Scientific Figures and Tables
Oral Talks 2 12:10 - 12:40 2 talks:
  • An Analysis of Tasks and Datasets in Peer Reviewing (Moritz Staudinger, Wojciech Kusa, Florina Piroi, Allan Hanbury) (in-person)
  • Controllable Citation Sentence Generation with Language Models (Nianlong Gu, Richard Hahnloser) (remote)
Lunch (+In-person Posters) 12:40 - 14:10 In-person posters:
  • Artificial Intuition: Efficient Classification of Scientific Abstracts (Harsh Sakhrani, Naseela Pervez, Anirudh Ravi Kumar, Fred Morstatter, Alexandra Graddy-Reed, Andrea Belz)
  • Zero-shot Scientific Claim Verification Using LLMs and Citation Text (Maxwell Bennett, Carlos Alvarez, Lucy Wang)
  • First Steps in Building a Knowledge Base of Mathematical Results (Shrey Mishra, Yacine Brihmouche, Théo Delemazure, Antoine Gauquier, Pierre Senellart)
  • CiteAssist: A System for Automated Preprint Citation and BibTeX Generation (Lars Benedikt Kaesberg, Terry Ruas, Jan Philip Wahle, Bela Gipp)
  • Researcher Representations Based on Aggregating Embeddings of Publication Titles: A Case Study in a Japanese Academic Database (Hiroyoshi Nagao, Marie Katsurai)
  • CSIRO-LT at Context24: Contextualising Scientific Figures and Tables in Scientific Literature (Necva Bölücü, Vincent Nguyen, Roelien C. Timmer, Huichen Yang, Maciej Rybinski, Stephen Wan, Sarvnaz Karimi)
  • OSX at Context24: How Well Can GPT Tackle Contexualizing Scientific Figures and Tables (Tosho Hirasawa)
  • Guiding Large Language Models via External Attention Prompting for Scientific Extreme Summarization (Yuan Chang, Ziyue Li, Xiaoqiu Le)
  • MISTI: Metadata-Informed Scientific Text and Image Representation through Contrastive Learning (Pawin Taechoyotin, Daniel Acuna)
  • Synthetic Context with LLM for Entity Linking from Scientific Tables (Yuji Oshima, Hiroyuki Shindo, Hiroki Teranishi, Hiroki Ouchi, Taro Watanabe)
  • Beyond Retrieval: Topic-based Alignment of Scientific Papers to Research Proposal (Rudra Nath Palit, Manasi Patwardhan, Lovekesh Vig, Gautam Shroff)
  • AutoRef: Generating Refinements of Reviews Given Guidelines (Soham Chitnis, Manasi Patwardhan, Ashwin Srinivasan, Tanmay Tulsidas Verlekar, Lovekesh Vig, Gautam Shroff)
  • Toward Related Work Generation with Structure and Novelty Statement (Kazuya Nishimura, Kuniaki Saito, Tosho Hirasawa, Yoshitaka Ushiku)
Remote posters:
  • Understanding Survey Paper Taxonomy about Large Language Models via Graph Representation Learning (Jun Zhuang, Casey Kennington)
  • Papilusion at DAGPap24: Paper or Illusion? Detecting AI-generated Scientific Papers (Nikita Andreev, Alexander Shirnin, Vladislav Mikhailov, Ekaterina Artemova)
  • Harnessing CLIP for Evidence Identification in Scientific Literature: A Multimodal Approach to Context24 Shared Task (Anukriti Kumar, Lucy Lu Wang)
  • An end-to-end entity recognition and disambiguation framework for identifying Author Affiliation from literature publications (Lianghong Lin, Wenxiu Xie, Zili Chen, Tianyong Hao)
  • Utilizing an Ensemble Model with Anomalous Label Smoothing to Detect Generated Scientific Papers (Yuan Zhao, Junruo Gao, Junlin Wang, Gang Luo, Liang Tang)
  • Cited Text Spans for Scientific Citation Text Generation (Xiangci Li, Yi-Hui Lee, Jessica Ouyang)
  • Multi-head Span-based Detector for AI-generated Fragments in Scientific Papers (German Gritsai, Ildar Khabutdinov, Andrey Grabovoy)
Keynote 3 14:10 - 14:50 Speaker: Heng Ji (University of Illinois at Urbana-Champaign, USA)
Title: AI Plays Medicinal Chemist
Oral Talks 3 14:50 - 15:30 3 talks:
  • Metadata Enhancement Using Large Language Models (Hyunju Song, Steven Bethard, Andrea Thomer) (remote)
  • Integrating Table Representations into Large Language Models for Improved Scholarly Document Comprehension (Buse Sibel Korkmaz, Antonio del Rio Chanona) (in-person)
  • Evaluating the Effectiveness of Retrieval-Augmented Large Language Models in Scientific Document Reasoning (Sai Munikoti, Anurag Acharya, Sridevi Wagle, Sameera Horawalavithana) (remote)
Break 2 + Networking 15:30 - 16:00
Keynote 4 16:00 - 16:40 Speaker: Anna Rogers (University of Copenhagen)
Title: Large language models as research assistants: workflows and challenges
Panel Discussion 16:40 - 17:20
Closing 17:20 - 17:30