SciDef: Automating Definition Extraction from Academic Literature with Large Language Models

• URL: http://arxiv.org/abs/2602.05413v1
• Date: Thu, 05 Feb 2026 07:52:08 GMT
• Title: SciDef: Automating Definition Extraction from Academic Literature with Large Language Models
• Authors: Filip Kučera, Christoph Mandl, Isao Echizen, Radu Timofte, Timo Spinde,
• Abstract summary: SciDef is an LLM-based pipeline for automated definition extraction.<n>We test SciDef on DefExtra & DefSim, novel datasets of human-extracted definitions and definition-pairs' similarity.
• Score: 42.50759003781739
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Definitions are the foundation for any scientific work, but with a significant increase in publication numbers, gathering definitions relevant to any keyword has become challenging. We therefore introduce SciDef, an LLM-based pipeline for automated definition extraction. We test SciDef on DefExtra & DefSim, novel datasets of human-extracted definitions and definition-pairs' similarity, respectively. Evaluating 16 language models across prompting strategies, we demonstrate that multi-step and DSPy-optimized prompting improve extraction performance. To evaluate extraction, we test various metrics and show that an NLI-based method yields the most reliable results. We show that LLMs are largely able to extract definitions from scientific literature (86.4% of definitions from our test-set); yet future work should focus not just on finding definitions, but on identifying relevant ones, as models tend to over-generate them. Code & datasets are available at https://github.com/Media-Bias-Group/SciDef.

Related papers

• Towards Automated Lexicography: Generating and Evaluating Definitions for Learner's Dictionaries [37.91511820811209]
  We study dictionary definition generation (DDG), i.e., the generation of non-contextualized definitions for given headwords.<n>Specifically, we address learner's dictionary definition generation (LDDG), where definitions should consist of simple words.
  arXiv  Detail & Related papers  (2026-01-05T07:11:24Z)
• MOLE: Metadata Extraction and Validation in Scientific Papers Using LLMs [48.73595915402094]
  MOLE is a framework that automatically extracts metadata attributes from scientific papers covering datasets of languages other than Arabic.<n>Our methodology processes entire documents across multiple input formats and incorporates robust validation mechanisms for consistent output.
  arXiv  Detail & Related papers  (2025-05-26T10:31:26Z)
• Idiosyncrasies in Large Language Models [54.26923012617675]
  We unveil and study idiosyncrasies in Large Language Models (LLMs)<n>We find that fine-tuning text embedding models on LLM-generated texts yields excellent classification accuracy.<n>We leverage LLM as judges to generate detailed, open-ended descriptions of each model's idiosyncrasies.
  arXiv  Detail & Related papers  (2025-02-17T18:59:02Z)
• ANLS* -- A Universal Document Processing Metric for Generative Large Language Models [40.94659575657584]
  This paper introduces a new metric for evaluating generative models called ANLS*.<n>The ANLS* metric extends existing ANLS metrics as a drop-in-replacement and is still compatible with previously reported ANLS scores.<n>We also benchmark a novel approach to generate prompts for documents, called SFT, against other prompting techniques such as LATIN.
  arXiv  Detail & Related papers  (2024-02-06T09:50:08Z)
• The Ups and Downs of Large Language Model Inference with Vocabulary Trimming by Language Heuristics [74.99898531299148]
  This research examines vocabulary trimming (VT) inspired by restricting embedding entries to the language of interest to bolster time and memory efficiency. We apply two languages to trim the full vocabulary - Unicode-based script filtering and corpus-based selection - to different language families and sizes. It is found that VT reduces the memory usage of small models by nearly 50% and has an upper bound of 25% improvement in generation speed.
  arXiv  Detail & Related papers  (2023-11-16T09:35:50Z)
• Did You Read the Instructions? Rethinking the Effectiveness of Task Definitions in Instruction Learning [74.70157466822612]
  We systematically study the role of task definitions in instruction learning. We find that model performance drops substantially when removing contents describing the task output. We propose two strategies to help models better leverage task instructions.
  arXiv  Detail & Related papers  (2023-06-01T21:11:24Z)
• Syntax and Semantics Meet in the "Middle": Probing the Syntax-Semantics Interface of LMs Through Agentivity [68.8204255655161]
  We present the semantic notion of agentivity as a case study for probing such interactions. This suggests LMs may potentially serve as more useful tools for linguistic annotation, theory testing, and discovery.
  arXiv  Detail & Related papers  (2023-05-29T16:24:01Z)
• PSG: Prompt-based Sequence Generation for Acronym Extraction [26.896811663334162]
  We propose a Prompt-based Sequence Generation (PSG) method for the acronym extraction task. Specifically, we design a template for prompting the extracted acronym texts with auto-regression. A position extraction algorithm is designed for extracting the position of the generated answers.
  arXiv  Detail & Related papers  (2021-11-29T02:14:38Z)
• CDM: Combining Extraction and Generation for Definition Modeling [8.487707405248242]
  We propose to combine extraction and generation for definition modeling. First extract self- and correlative definitional information of target terms from the Web. Then generate the final definitions by incorporating the extracted definitional information.
  arXiv  Detail & Related papers  (2021-11-14T08:03:18Z)
• Revisiting Self-Training for Few-Shot Learning of Language Model [61.173976954360334]
  Unlabeled data carry rich task-relevant information, they are proven useful for few-shot learning of language model. In this work, we revisit the self-training technique for language model fine-tuning and present a state-of-the-art prompt-based few-shot learner, SFLM.
  arXiv  Detail & Related papers  (2021-10-04T08:51:36Z)
• Toward Cross-Lingual Definition Generation for Language Learners [10.45755551957024]
  We propose to generate definitions in English for words in various languages. Models can be directly applied to other languages after trained on the English dataset. Experiments and manual analyses show that our models have a strong cross-lingual transfer ability.
  arXiv  Detail & Related papers  (2020-10-12T08:45:28Z)
• Lexical Sememe Prediction using Dictionary Definitions by Capturing Local Semantic Correspondence [94.79912471702782]
  Sememes, defined as the minimum semantic units of human languages, have been proven useful in many NLP tasks. We propose a Sememe Correspondence Pooling (SCorP) model, which is able to capture this kind of matching to predict sememes. We evaluate our model and baseline methods on a famous sememe KB HowNet and find that our model achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2020-01-16T17:30:36Z)

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.