paper-with-me

Papers

Learning Interpretable Style Embeddings via Prompting LLMs

2023-05-22 · Ajay Patel, Delip Rao, Ansh Kothary, Kathleen McKeown, Chris Callison-Burch

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.

📄 PDF Abstract BibTeX arXiv:2305.12696

Code (0)

등록된 구현이 없습니다.

Tasks

Authorship AttributionRepresentation Learning

Similar Papers 제목 키워드 기반

How Well Do LLMs Imitate Human Writing Style?

2025-09-29 · Rebira Jemama, Rajesh Kumar arxiv

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

2024-05-26 · Vinamra Benara, Chandan Singh, John X. Morris, Richard Antonello 외

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 Answering

Steering Large Language Models with Register Analysis for Arbitrary Style Transfer

2025-05-01 · Xinchen Yang, Marine Carpuat

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 Transfer

Interpretable User Satisfaction Estimation for Conversational Systems with Large Language Models

2024-03-19 · Ying-Chun Lin, Jennifer Neville, Jack W. Stokes, Longqi Yang 외

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…

Chatbot

Interpreting Style Representations via Style-Eliciting Prompts

2026-06-04 · Junghwan Kim, David Jurgens arxiv

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