Learning Interpretable Style Embeddings via Prompting LLMs
Style representation learning builds content-independent representations of author style in text. Stylometry, the analysis of style in text, is often performed by expert forensic linguists and no large dataset of stylometric annotations exists for training. Current style representation learning uses neural methods to disentangle style from content to create style vectors, however, these approaches result in uninterpretable representations, complicating their usage in downstream applications like authorship attribution where auditing and explainability is critical. In this work, we use prompting to perform stylometry on a large number of texts to create a synthetic dataset and train human-interpretable style representations we call LISA embeddings. We release our synthetic stylometry dataset and our interpretable style models as resources.
Code (0)
등록된 구현이 없습니다.
Tasks
Authorship AttributionRepresentation LearningSimilar Papers 제목 키워드 기반
How Well Do LLMs Imitate Human Writing Style?
Large language models (LLMs) can generate fluent text, but their ability to replicate the distinctive style of a specific human author remains unclear. We present a fast, training-free framework for authorship verificati…
Crafting Interpretable Embeddings by Asking LLMs Questions
Large language models (LLMs) have rapidly improved text embeddings for a growing array of natural-language processing tasks. However, their opaqueness and proliferation into scientific domains such as neuroscience have c…
Question AnsweringSteering Large Language Models with Register Analysis for Arbitrary Style Transfer
Large Language Models (LLMs) have demonstrated strong capabilities in rewriting text across various styles. However, effectively leveraging this ability for example-based arbitrary style transfer, where an input text is …
Style TransferInterpretable User Satisfaction Estimation for Conversational Systems with Large Language Models
Accurate and interpretable user satisfaction estimation (USE) is critical for understanding, evaluating, and continuously improving conversational systems. Users express their satisfaction or dissatisfaction with diverse…
ChatbotInterpreting Style Representations via Style-Eliciting Prompts
Style representation learning is a powerful tool for authorship analysis and modeling writing style, yet the latent nature of learned representations makes them difficult to interpret. Recent work has attempted to explai…
Representation Learning