{"ID":2845950,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.03830","arxiv_id":"2511.03830","title":"Divide, Cache, Conquer: Dichotomic Prompting for Efficient Multi-Label LLM-Based Classification","abstract":"We introduce a method for efficient multi-label text classification with large language models (LLMs), built on reformulating classification tasks as sequences of dichotomic (yes/no) decisions. Instead of generating all labels in a single structured response, each target dimension is queried independently, which, combined with a prefix caching mechanism, yields substantial efficiency gains for short-text inference without loss of accuracy. To demonstrate the approach, we focus on affective text analysis, covering 24 dimensions including emotions and sentiment. Using LLM-to-SLM distillation, a powerful annotator model (DeepSeek-V3) provides multiple annotations per text, which are aggregated to fine-tune smaller models (HerBERT-Large, CLARIN-1B, PLLuM-8B, Gemma3-1B). The fine-tuned models show significant improvements over zero-shot baselines, particularly on the dimensions seen during training. Our findings suggest that decomposing multi-label classification into dichotomic queries, combined with distillation and cache-aware inference, offers a scalable and effective framework for LLM-based classification. While we validate the method on affective states, the approach is general and applicable across domains.","short_abstract":"We introduce a method for efficient multi-label text classification with large language models (LLMs), built on reformulating classification tasks as sequences of dichotomic (yes/no) decisions. Instead of generating all labels in a single structured response, each target dimension is queried independently, which, combi...","url_abs":"https://arxiv.org/abs/2511.03830","url_pdf":"https://arxiv.org/pdf/2511.03830v1","authors":"[\"Mikołaj Langner\",\"Jan Eliasz\",\"Ewa Rudnicka\",\"Jan Kocoń\"]","published":"2025-11-05T19:53:51Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}