Metraipolis › archive › dc_21731fda0cd8
How Many Examples, and Which Ones? A Study of In-Context Learning for Natural Language Inference — arXiv:2611.09936
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.09936
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-10T18:42:01.789Z
- SHA-256 of the archived text
ff28d3d6de4eb3e5060a103fdaefadf2e923425fb7e96c3df553baf270d9f22f- Stable URL of this page
https://metraipolis.com/documento/dc_21731fda0cd8
How to cite
How Many Examples, and Which Ones? A Study of In-Context Learning for Natural Language Inference — arXiv:2611.09936 — arXiv (en), https://arxiv.org/abs/2611.09936 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_21731fda0cd8 (Metraipolis archive dc_21731fda0cd8, sha256 ff28d3d6de4eb3e5060a103fdaefadf2e923425fb7e96c3df553baf270d9f22f)
BibTeX
@misc{dc21731fda0cd8,
title = {How Many Examples, and Which Ones? A Study of In-Context Learning for Natural Language Inference — arXiv:2611.09936},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.09936},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_21731fda0cd8; sha256 ff28d3d6de4eb3e5060a103fdaefadf2e923425fb7e96c3df553baf270d9f22f},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.09936. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Natural language inference (NLI) is a fundamental task of natural language processing and crucial for evaluating the strengths and weaknesses of AI methods. Research has mostly focused on encoder or encoder-decoder architectures. However, the field of decoder-only Large Language Models (LLMs) remains underexplored. While prior work has mainly investigated complex sampling and prompting techniques, the effectiveness of a minimalistic prompting approach is yet to be examined in decoder-only LLMs. In this work, we examine and provide a comprehensive benchmark of LLMs (Llama, Mistral, Gemma, and Phi 4) in this domain, across the MNLI, QNLI and SciTail datasets. The performance of these models was evaluated using zero-shot and few-shot prompting strategies with simple and direct prompts. The results of the article indicate that LLMs generally perform exceptionally well when they are provided with a simple, straightforward prompt, challenging the notion that complex prompting techniques are always required for NLI tasks. Additionally, we find that the choice of demonstration label in one-shot prompting significantly affects performance for most models, with entailment-primed examples performing best. Our findings also show that the use of a few representative examples, in the case of few-shot, produced performance comparable or superior to prompts with higher example counts, although the efficacy of the prompting techniques is model and dataset-dependent. Moreover, our simple prompting approach consistently matched or outperformed more elaborate methods such as ICS and MCQ-based prompting. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2611.09936 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-10T18:37:37.560Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).