The reviewed record of science sign in
Pith

arxiv: 2305.03514 · v3 · pith:ZBF2VJ77 · submitted 2023-04-12 · cs.CL · cs.LG

Can Large Language Models Transform Computational Social Science?

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:ZBF2VJ77record.jsonopen to challenge →

classification cs.CL cs.LG
keywords llmslanguagemodelssocialtaskszero-shotpipelinescience
0
0 comments X
read the original abstract

Large Language Models (LLMs) are capable of successfully performing many language processing tasks zero-shot (without training data). If zero-shot LLMs can also reliably classify and explain social phenomena like persuasiveness and political ideology, then LLMs could augment the Computational Social Science (CSS) pipeline in important ways. This work provides a road map for using LLMs as CSS tools. Towards this end, we contribute a set of prompting best practices and an extensive evaluation pipeline to measure the zero-shot performance of 13 language models on 25 representative English CSS benchmarks. On taxonomic labeling tasks (classification), LLMs fail to outperform the best fine-tuned models but still achieve fair levels of agreement with humans. On free-form coding tasks (generation), LLMs produce explanations that often exceed the quality of crowdworkers' gold references. We conclude that the performance of today's LLMs can augment the CSS research pipeline in two ways: (1) serving as zero-shot data annotators on human annotation teams, and (2) bootstrapping challenging creative generation tasks (e.g., explaining the underlying attributes of a text). In summary, LLMs are posed to meaningfully participate in social science analysis in partnership with humans.

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 5 Pith papers

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

  1. LLM Agents for Deliberative Collaboration: A Study on Joint Decision Making Under Partial Observability

    cs.CL 2026-07 conditional novelty 6.0

    A benchmark for LLM agents in partially observable joint decision-making reveals that deliberation challenges current models but can enable reflection and error correction.

  2. A Roadmap to Pluralistic Alignment

    cs.AI 2024-02 unverdicted novelty 6.0

    The paper formalizes three types of pluralistic AI models and three benchmark classes, arguing that current alignment techniques may reduce rather than increase distributional pluralism.

  3. A Survey on Large Language Model based Autonomous Agents

    cs.AI 2023-08 accept novelty 6.0

    A survey of LLM-based autonomous agents that proposes a unified framework for their construction and reviews applications in social science, natural science, and engineering along with evaluation methods and future di...

  4. AI-Augmented Surveys: Leveraging Large Language Models and Surveys for Opinion Prediction

    cs.CL 2023-05 unverdicted novelty 6.0

    LLM embeddings enable strong retrodiction of masked GSS opinions via cross-validation and external validation but only modest performance on entirely unasked opinions.

  5. Characterizing initial human-AI proof formalization workflows

    cs.AI 2026-06 unverdicted novelty 5.0

    A controlled user study and qualitative survey find that AI assistance raises formalization accuracy for math proofs, with users flexibly combining multiple tools while retaining oversight.