Reasoning Graph Enhanced Exemplars Retrieval for In-Context Learning
保存先:
| 出版年: | arXiv.org (Dec 12, 2024), p. n/a |
|---|---|
| 第一著者: | |
| その他の著者: | , , , |
| 出版事項: |
Cornell University Library, arXiv.org
|
| 主題: | |
| オンライン･アクセス: | Citation/Abstract Full text outside of ProQuest |
| タグ: |
タグなし, このレコードへの初めてのタグを付けませんか!
|
MARC
| LEADER | 00000nab a2200000uu 4500 | ||
|---|---|---|---|
| 001 | 3106537543 | ||
| 003 | UK-CbPIL | ||
| 022 | |a 2331-8422 | ||
| 035 | |a 3106537543 | ||
| 045 | 0 | |b d20241212 | |
| 100 | 1 | |a Lin, Yukang | |
| 245 | 1 | |a Reasoning Graph Enhanced Exemplars Retrieval for In-Context Learning | |
| 260 | |b Cornell University Library, arXiv.org |c Dec 12, 2024 | ||
| 513 | |a Working Paper | ||
| 520 | 3 | |a Large language models (LLMs) have exhibited remarkable few-shot learning capabilities and unified the paradigm of NLP tasks through the in-context learning (ICL) technique. Despite the success of ICL, the quality of the exemplar demonstrations can significantly influence the LLM's performance. Existing exemplar selection methods mainly focus on the semantic similarity between queries and candidate exemplars. On the other hand, the logical connections between reasoning steps can be beneficial to depict the problem-solving process as well. In this paper, we proposes a novel method named Reasoning Graph-enhanced Exemplar Retrieval (RGER). RGER first quires LLM to generate an initial response, then expresses intermediate problem-solving steps to a graph structure. After that, it employs graph kernel to select exemplars with semantic and structural similarity. Extensive experiments demonstrate the structural relationship is helpful to the alignment of queries and candidate exemplars. The efficacy of RGER on math and logit reasoning tasks showcases its superiority over state-of-the-art retrieval-based approaches. Our code is released at https://github.com/Yukang-Lin/RGER. | |
| 653 | |a Problem solving | ||
| 653 | |a Similarity | ||
| 653 | |a Semantics | ||
| 653 | |a Large language models | ||
| 653 | |a Context | ||
| 653 | |a Query processing | ||
| 653 | |a Reasoning | ||
| 653 | |a Retrieval | ||
| 700 | 1 | |a Zhong, Bingchen | |
| 700 | 1 | |a Jiang, Shuoran | |
| 700 | 1 | |a Siebert, Joanna | |
| 700 | 1 | |a Chen, Qingcai | |
| 773 | 0 | |t arXiv.org |g (Dec 12, 2024), p. n/a | |
| 786 | 0 | |d ProQuest |t Engineering Database | |
| 856 | 4 | 1 | |3 Citation/Abstract |u https://www.proquest.com/docview/3106537543/abstract/embedded/ZKJTFFSVAI7CB62C?source=fedsrch |
| 856 | 4 | 0 | |3 Full text outside of ProQuest |u http://arxiv.org/abs/2409.11147 |