Overview

This field studies how large language models can help create labels and structured metadata for text, images, audio, video, and specialized records. Common approaches include prompt and codebook design, retrieval-augmented examples, model ensembles, confidence-based review, and training smaller classifiers on generated labels. These methods can reduce annotation time and cost, especially in low-resource or domain-specific settings, but their usefulness depends on careful validation against expert judgments and downstream tasks. A central challenge is that agreement and repeatability do not guarantee valid labels: results can shift with prompts, models, task definitions, and demographic cues, so human oversight and transparent error analysis remain important.

Latest papers

217 papers18 papers in the last four weeks, down 28% on the four weeks before. 0.1% of all new papers.

Jul 29, 2025

Introducing HALC: A general pipeline for the systematic and reliable construction of prompts for automated coding with LLMs in the computational social sciences

LLMs are seeing widespread use for task automation, including automated coding in the social sciences. However, even though researchers have proposed different prompting strategies, their effectiveness varies across LLMs and tasks. Often trial and error practices are still widespread. Our study aims to fill this gap and evaluate how LLMs can be used in a systematic and transparent way to produce reliable codings in content analyses. We propose HALC-a general pipeline that allows for the systematic and reliable construction of prompts for any given coding task and model. We develop this pipeline based on current literature and findings of a prestudy investigating consistency and influencing factors of LLM codings. We also apply HALC on two other datasets covering different thematic contexts, document types, languages, and coding units to test its applicability. Based on more than three million LLM requests, our results demonstrate that the pipeline is capable of identifying prompts for reliable codings in different settings. We also discuss shortcomings and further potential for development.
Feb 28, 2025

AnnoCaseLaw: Legal Annotation Benchmark of Civil Negligence

Language models offer a way to scale costly, labour-intensive expert annotation, but their ability to reproduce expert judgements remains uncertain. This is particularly challenging in law, where annotators must distinguish the reasoning supporting judicial decisions from other legally relevant discussion. We present AnnoCaseLaw as a densely annotated benchmark comprising 471471 U.S. civil-negligence court opinions with more than 12,00012,000 expert highlights across five annotation categories. We evaluate proprietary frontier, open-weight, legal-specialised, and decision models on their ability to reproduce these annotations. Models perform better on Facts and Outcome than on Application of Law to Facts, Procedural History, and Relevant Precedents. On Application of Law to Facts, proprietary frontier models achieve the strongest balance of reasoning coverage and precision, while the open-weight model Gemma 4 achieves comparable Macro-F1 to proprietary frontier models at a fraction of the estimated inference cost. Our findings highlight the importance of evaluating annotation coverage and cost alongside aggregate scores when assessing the feasibility of automated legal annotation.
Nov 6, 2024

Harmful YouTube Video Detection: A Taxonomy of Online Harm and MLLMs as Alternative Annotators

Video platforms, used by billions globally, are criticized for exposing users to harmful content. Yet, detecting online harm remains challenging due to inconsistent approaches to what constitutes harm and limitations of human annotation. We address both challenges. Theoretically, we integrate and expand existing taxonomies and platform guidelines to multimodal contexts and develop a comprehensive taxonomy for online harm. We categorize online harm on video platforms into six content-based categories: Information, Hate and harassment, Addictive, Clickbait, Sexual, and Physical harms. Methodologically, we propose and systematically test multimodal large language models (MLLMs) as alternative annotators of harmful videos. We curate a dataset of 19,422 potentially harmful YouTube videos and annotate them using GPT-4-Turbo, non-trained crowdworkers, and trained annotators. We discuss the potential applications of MLLMs in platform content moderation and social science research, particularly in contexts where they perform comparably to human annotators in binary and multi-label classification tasks.
Oct 17, 2024

Transferring Natural Language Datasets Between Languages Using Large Language Models for Modern Decision Support and Sci-Tech Analytical Systems

The decision-making process to rule R&D relies on information related to current trends in particular research areas. In this work, we investigated how one can use large language models (LLMs) to transfer the dataset and its annotation from one language to another. This is crucial since sharing knowledge between different languages could boost certain underresourced directions in the target language, saving lots of effort in data annotation or quick prototyping. We experiment with English and Russian pairs, translating the DEFT (Definition Extraction from Texts) corpus. This corpus contains three layers of annotation dedicated to term-definition pair mining, which is a rare annotation type for Russian. The presence of such a dataset is beneficial for the natural language processing methods of trend analysis in science since the terms and definitions are the basic blocks of any scientific field. We provide a pipeline for the annotation transfer using LLMs. In the end, we train the BERT-based models on the translated dataset to establish a baseline.
Oct 11, 2024

Which Demographics do LLMs Default to During Annotation?

Demographics and cultural background of annotators influence the labels they assign in text annotation -- for instance, an elderly woman might find it offensive to read a message addressed to a "bro", but a male teenager might find it appropriate. It is therefore important to acknowledge label variations to not under-represent members of a society. Two research directions developed out of this observation in the context of using large language models (LLM) for data annotations, namely (1) studying biases and inherent knowledge of LLMs and (2) injecting diversity in the output by manipulating the prompt with demographic information. We combine these two strands of research and ask the question to which demographics an LLM resorts to when no demographics is given. To answer this question, we evaluate which attributes of human annotators LLMs inherently mimic. Furthermore, we compare non-demographic conditioned prompts and placebo-conditioned prompts (e.g., "you are an annotator who lives in house number 5") to demographics-conditioned prompts ("You are a 45 year old man and an expert on politeness annotation. How do you rate {instance}"). We study these questions for politeness and offensiveness annotations on the POPQUORN data set, a corpus created in a controlled manner to investigate human label variations based on demographics which has not been used for LLM-based analyses so far. We observe notable influences related to gender, race, and age in demographic prompting, which contrasts with previous studies that found no such effects.
Mar 26, 2024

"You are an expert annotator": Automatic Best-Worst-Scaling Annotations for Emotion Intensity Modeling

Labeling corpora constitutes a bottleneck to create models for new tasks or domains. Large language models mitigate the issue with automatic corpus labeling methods, particularly for categorical annotations. Some NLP tasks such as emotion intensity prediction, however, require text regression, but there is no work on automating annotations for continuous label assignments. Regression is considered more challenging than classification: The fact that humans perform worse when tasked to choose values from a rating scale lead to comparative annotation methods, including best-worst scaling. This raises the question if large language model-based annotation methods show similar patterns, namely that they perform worse on rating scale annotation tasks than on comparative annotation tasks. To study this, we automate emotion intensity predictions and compare direct rating scale predictions, pairwise comparisons and best-worst scaling. We find that the latter shows the highest reliability. A transformer regressor fine-tuned on these data performs nearly on par with a model trained on the original manual annotations.
Jul 12, 2023

Can Large Language Models Aid in Annotating Speech Emotional Data? Uncovering New Frontiers

Despite recent advancements in speech emotion recognition (SER) models, state-of-the-art deep learning (DL) approaches face the challenge of the limited availability of annotated data. Large language models (LLMs) have revolutionised our understanding of natural language, introducing emergent properties that broaden comprehension in language, speech, and vision. This paper examines the potential of LLMs to annotate abundant speech data, aiming to enhance the state-of-the-art in SER. We evaluate this capability across various settings using publicly available speech emotion classification datasets. Leveraging ChatGPT, we experimentally demonstrate the promising role of LLMs in speech emotion data annotation. Our evaluation encompasses single-shot and few-shots scenarios, revealing performance variability in SER. Notably, we achieve improved results through data augmentation, incorporating ChatGPT-annotated samples into existing datasets. Our work uncovers new frontiers in speech emotion classification, highlighting the increasing significance of LLMs in this field moving forward.