The reviewed record of science sign in
Pith

arxiv: 2307.12973 · v2 · pith:MVO7J72Q · submitted 2023-07-24 · cs.CL

Wisdom of Instruction-Tuned Language Model Crowds. Exploring Model Label Variation

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:MVO7J72Qrecord.jsonopen to challenge →

classification cs.CL
keywords humanlabelmodelmodelsannotationhoweverllmstasks
0
0 comments X
read the original abstract

Large Language Models (LLMs) exhibit remarkable text classification capabilities, excelling in zero- and few-shot learning (ZSL and FSL) scenarios. However, since they are trained on different datasets, performance varies widely across tasks between those models. Recent studies emphasize the importance of considering human label variation in data annotation. However, how this human label variation also applies to LLMs remains unexplored. Given this likely model specialization, we ask: Do aggregate LLM labels improve over individual models (as for human annotators)? We evaluate four recent instruction-tuned LLMs as annotators on five subjective tasks across four languages. We use ZSL and FSL setups and label aggregation from human annotation. Aggregations are indeed substantially better than any individual model, benefiting from specialization in diverse tasks or languages. Surprisingly, FSL does not surpass ZSL, as it depends on the quality of the selected examples. However, there seems to be no good information-theoretical strategy to select those. We find that no LLM method rivals even simple supervised models. We also discuss the tradeoffs in accuracy, cost, and moral/ethical considerations between LLM and human annotation.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Security and Privacy Prompts in the Wild: What Users Ask LLMs and How LLMs Respond

    cs.CL 2026-06 unverdicted novelty 7.0

    Analysis of 14,727 security and privacy prompts from WildChat finds commercial LLMs give higher-quality responses than open-weight models but can produce inconsistent answers across repeated queries.