# Enhancing Automatic Term Extraction with Large Language Models via Syntactic Retrieval

arXiv: https://arxiv.org/abs/2506.21222 · HTML: https://mlsanity.com/paper/2506.21222/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 48 references that are in the map.
- First posted on arXiv 26 Jun 2025.

## Builds on (most cited first, 21 of 21)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Gemma 2: Improving Open Language Models at a Practical Size](https://mlsanity.com/paper/2408.00118/) (2024)
- [ChatIE: Zero-Shot Information Extraction via Chatting with ChatGPT](https://mlsanity.com/paper/2302.10205/) (2023)
- [Large Language Models for Generative Information Extraction: A Survey](https://mlsanity.com/paper/2312.17617/) (2023)
- [InstructUIE: Multi-task Instruction Tuning for Unified Information Extraction](https://mlsanity.com/paper/2304.08085/) (2023)
- [Large Language Model Is Not a Good Few-shot Information Extractor, but a Good Reranker for Hard Samples!](https://mlsanity.com/paper/2303.08559/) (2023)
- [GoLLIE: Annotation Guidelines improve Zero-Shot Information-Extraction](https://mlsanity.com/paper/2310.03668/) (2023)
- [Finding Universal Grammatical Relations in Multilingual BERT](https://mlsanity.com/paper/2005.04511/) (2020)
- [Making Text Embedders Few-Shot Learners](https://mlsanity.com/paper/2409.15700/) (2024)
- [Fast and Accurate Neural CRF Constituency Parsing](https://mlsanity.com/paper/2008.03736/) (2020)
- [Aligning Instruction Tasks Unlocks Large Language Models as Zero-Shot Relation Extractors](https://mlsanity.com/paper/2305.11159/) (2023)
- [Prompting Language Models for Linguistic Structure](https://mlsanity.com/paper/2211.07830/) (2022)
- [Chain of Thought with Explicit Evidence Reasoning for Few-shot Relation Extraction](https://mlsanity.com/paper/2311.05922/) (2023)
- [Investigating semantic subspaces of Transformer sentence embeddings through linear structural probing](https://mlsanity.com/paper/2310.11923/) (2023)
- [FastKASSIM: A Fast Tree Kernel-Based Syntactic Similarity Metric](https://mlsanity.com/paper/2203.08299/) (2022)
- [On the Evolution of Syntactic Information Encoded by BERT's Contextualized Representations](https://mlsanity.com/paper/2101.11492/) (2021)
- [The Recent Advances in Automatic Term Extraction: A survey](https://mlsanity.com/paper/2301.06767/) (2023)

## Abstract (arXiv)

Automatic Term Extraction (ATE) identifies domain-specific expressions that are crucial for downstream tasks such as machine translation and information retrieval. Although large language models (LLMs) have significantly advanced various NLP tasks, their potential for ATE has scarcely been examined. We propose a retrieval-based prompting strategy that, in the few-shot setting, selects demonstrations according to syntactic rather than semantic similarity. This syntactic retrieval method is domain-agnostic and provides more reliable guidance for capturing term boundaries. We evaluate the approach in both in-domain and cross-domain settings, analyzing how lexical overlap between the query sentence and its retrieved examples affects performance. Experiments on three specialized ATE benchmarks show that syntactic retrieval improves F1-score. These findings highlight the importance of syntactic cues when adapting LLMs to terminology-extraction tasks.