Abstract:This paper presents several strategies to automatically obtain additional examples for in-context learning, effectively transforming relation extraction from a 1-shot to a few-shot setting. Specifically, we introduce a novel strategy for example selection, in which new examples are selected based on the similarity of their underlying syntactic-semantic structure to the provided 1-shot example. We show that our strategy results in complementary word choices and sentence structures compared to LLM-generated examples. When both strategies are combined, the resulting hybrid system achieves a more holistic picture of the relations of interest than either method alone. Our framework transfers well across datasets (FS-TACRED and FS-FewRel) and LLM families (Qwen and Gemma). Overall, our hybrid system consistently outperforms alternative strategies achieving state-of-the-art performance on FS-TACRED and strong gains on a customized FewRel subset.
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2601.20803 [cs.CL] |
| (or arXiv:2601.20803v2 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2601.20803 arXiv-issued DOI via DataCite |
Submission history
From: Aunabil Chakma [view email]
[v1]
Wed, 28 Jan 2026 17:48:58 UTC (297 KB)
[v2]
Fri, 29 May 2026 21:18:02 UTC (152 KB)