Causal Representation Enhances Cross-Domain Named Entity Recognition in Large Language Models
Source abstract
Abstract
Large language models cross-domain named entity recognition task in the face of the scarcity of large language labeled data in a specific domain, due to the entity bias arising from the variation of entity information between... | Find, read and cite all the research you need on Tech Science Press
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Topic Modeling · Natural Language Processing Techniques · Data Quality and Management
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (39)
Show source-provided references
1. Brown TB, Mann B, Ryder N. Language models are few-shot learners. arXiv:2005.14165. 2020.
2. Alqaaidi SK, Bozorgi E. A survey on recent named entity recognition and relation classification methods with focus on few-shot learning approaches. arXiv:2310.19055. 2023.10.5220/0012791600003756 ↗
3. Wei J, Wang X. Chain of thought prompting elicits reasoning in large language models. arXiv:2201.11903. 2022.
4. Evolution and prospects of foundation models: from large language models to large multimodal models
5. Causal inspired trustworthy machine learning
6. SEAG: structure-aware event causality generation
7. Lin J, Zhou J, Chen Q. Causal intervention-based prompt debiasing for event argument extraction. arXiv:2210.01561. 2022.
8. Ren · Findings of the association for computational linguistics: EMNLP 2023 · 2023 · 2627
9. A label-aware autoregressive framework for cross-domain NER
10. Causal intervention-based few-shot named entity recognition
11. Kalyan KS. A survey of GPT-3 family large language models including ChatGPT and GPT-4. arXiv:2310.12321. 2023.10.2139/ssrn.4593895 ↗
12. How transferable are neural networks in NLP applications?
13. DoSEA: a domain-specific entity-aware framework for cross-domain named entity recogition
14. A unified MRC framework for named entity recognition
15. Multi-domain named entity recognition with genre-aware and agnostic inference
16. CONTaiNER: few-shot named entity recognition via contrastive learning
17. Improving named entity recognition via bridge-based domain adaptation
18. Han R, Yang C, Peng T. An empirical study on information extraction using large language models. arXiv:2305.14450. 2024.
19. Qin C, Zhang A, Zhang Z. Is ChatGPT a general-purpose natural language processing task solver? arXiv:2302.06476. 2023.10.18653/v1/2023.emnlp-main.85 ↗
20. Mitigating label biases for in-context learning
21. A causal view of entity bias in (Large) language models
22. Ye J, Xu N, Wang Y, Zhou J, Zhang Q, Gui T, et al. LLM-DA: data augmentation via large language models for few-shot named entity recognition. arXiv:2402.14568. 2024.
23. Thinking about GPT-3 In-context learning for biomedical IE? Think again
24. Aligning instruction tasks unlocks large language models as zero-shot relation extractors
25. Tang K, Niu Y, Huang J. Unbiased scene graph generation from biased training. arXiv:2002.11949. 2020.10.1109/CVPR42600.2020.00377 ↗
26. Lin Z, Ding H, Hoang NT. Pre-trained recommender systems: a causal debiasing perspective. arXiv:2310.19251. 2024.10.1145/3616855.3635779 ↗
27. Can prompt probe pretrained language models? Understanding the invisible risks from a causal view
28. Cross-domain Named entity recognition via graph matching
29. Introduction to the CoNLL-2003 Shared Task: language-Independent Named Entity Recognition
30. Overview of BioNLP shared task 2013
31. Asgard: a portable architecture for multilingual dialogue systems
32. Liu Z, Xu Y, Yu T, Dai W, Ji Z, Cahyawijaya S, et al. CrossNER: evaluating cross-domain named entity recognition. arXiv:2012.04373. 2020.10.1609/aaai.v35i15.17587 ↗
33. BERT: pre-training of deep bidirectional transformers for language understanding
34. Coach: a coarse-to-fine approach for cross-domain slot filling
35. Simple and effective few-shot named entity recognition with structured nearest neighbor learning
36. LightNER: a lightweight tuning paradigm for low-resource NER via pluggable prompting
37. Template-free prompt tuning for few-shot NER
38. Chen X, Li L, Qiao S. One model for all domains: collaborative domain-prefix tuning for cross-domain NER. arXiv:2301.10410. 2023.10.24963/ijcai.2023/559 ↗
39. Ma Y, Cao Y, Hong Y. Large language model is not a good few-shot information extractor, but a good reranker for hard samples! In: Findings of the Association for Computational Linguistics: EMNLP 2023; 2023; Singapore: Association for Computational Linguistics. p. 10572–601.10.18653/v1/2023.findings-emnlp.710 ↗