Metraipolis › archive › dc_a82ecb660683
SALA: Semantic-Aware Logical Alignment for Complex Reasoning in In-Context Learning — arXiv:2609.02336
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.02336
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T03:26:26.361Z
- SHA-256 of the archived text
9d73fa889bf42c714bf5771228a4a6eb9265d74f57188b39c499405a70780fb5- Stable URL of this page
https://metraipolis.com/documento/dc_a82ecb660683
How to cite
SALA: Semantic-Aware Logical Alignment for Complex Reasoning in In-Context Learning — arXiv:2609.02336 — arXiv (en), https://arxiv.org/abs/2609.02336 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a82ecb660683 (Metraipolis archive dc_a82ecb660683, sha256 9d73fa889bf42c714bf5771228a4a6eb9265d74f57188b39c499405a70780fb5)
BibTeX
@misc{dca82ecb660683,
title = {SALA: Semantic-Aware Logical Alignment for Complex Reasoning in In-Context Learning — arXiv:2609.02336},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.02336},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a82ecb660683; sha256 9d73fa889bf42c714bf5771228a4a6eb9265d74f57188b39c499405a70780fb5},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.02336. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Effective in-context learning (ICL) for complex reasoning relies on selecting the right demonstrations. Traditional retrieval methods based on surface similarity fail to capture the underlying problem-solving logic. Recent logic-based methods address this by matching predefined reasoning steps, but the rigid rules and exact-match criteria is improper to handle flexible or diverse reasoning processes. To address the problem, we propose SALA, a Semantic-Aware Logical Alignment framework. Instead of relying on a fixed inventory, SALA automatically learns task-specific reasoning operations. It then embeds these operations into a continuous semantic space and uses dynamic time warping (DTW) to align the reasoning sequences. This approach allows for soft, flexible matching of reasoning logic while remaining highly interpretable. Experiments across four reasoning benchmarks and three LLMs demonstrate that SALA outperforms existing demonstration selection methods. Further analysis confirms the roles of the operation induction and the logical semantic alignment. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-03 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2609.02336 — 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 2026-10-17T03:13:12.440Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-03?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).