SALSA: Single-pass Autoregressive LLM Structured Classification

ACL ARR 2025 May Submission2155 Authors

Abstract: Despite their impressive generalization capabilities, instruction-tuned Large Language Models often underperform on text classification benchmarks. We introduce SALSA, a coherent pipeline that combines structured prompting, class-to-token mapping, and parameter-efficient fine-tuning, thereby avoiding cold-start training. Each class label is mapped to a distinct output token, and prompts are constructed to elicit a single-token response. During inference, the model’s output is projected only onto the logits of the relevant class tokens, enabling efficient and accurate classification in a single forward pass. SALSA achieves state-of-the-art results across diverse benchmarks, demonstrating its robustness and scalability for LLM-based classification applications.

Paper Type: Short

Research Area: Efficient/Low-Resource Methods for NLP

Research Area Keywords: LLM Efficiency, data-efficient training, fine-tuning, prompting, parameter-efficient-training, clinical NLP, hate speech detection

Contribution Types: NLP engineering experiment, Approaches low compute settings-efficiency

Languages Studied: English

Submission Number: 2155