SALSA: Single-pass Autoregressive LLM Structured Classification

TL;DR

SALSA is a novel classification method that uses structured prompting and class-to-token mapping to enable efficient, single-pass inference with large language models, achieving state-of-the-art results.

Contribution

It introduces a new pipeline combining structured prompting, class-to-token mapping, and parameter-efficient fine-tuning for LLM classification.

Findings

Achieves state-of-the-art results on multiple benchmarks.

Enables single-pass inference without cold-start training.

Demonstrates robustness and scalability in LLM classification.

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.