paper-with-me

홈 › Papers

Alfred: A System for Prompted Weak Supervision

2023-05-29 · Peilin Yu, Stephen Bach

Alfred is the first system for programmatic weak supervision (PWS) that creates training data for machine learning by prompting. In contrast to typical PWS systems where weak supervision sources are programs coded by experts, Alfred enables users to encode their subject matter expertise via natural language prompts for language and vision-language models. Alfred provides a simple Python interface for the key steps of this emerging paradigm, with a high-throughput backend for large-scale data labeling. Users can quickly create, evaluate, and refine their prompt-based weak supervision sources; map the results to weak labels; and resolve their disagreements with a label model. Alfred enables a seamless local development experience backed by models served from self-managed computing clusters. It automatically optimizes the execution of prompts with optimized batching mechanisms. We find that this optimization improves query throughput by 2.9x versus a naive approach. We present two example use cases demonstrating Alfred on YouTube comment spam detection and pet breeds classification. Alfred is open source, available at https://github.com/BatsResearch/alfred.

📄 PDF Abstract BibTeX arXiv:2305.18623

Code (1)

batsresearch/alfred 공식 구현 pytorch

Tasks

Spam detection

Similar Papers 제목 키워드 기반

Leveraging Large Language Models for Structure Learning in Prompted Weak Supervision

2024-02-02 · Jinyan Su, Peilin Yu, Jieyu Zhang, Stephen H. Bach

Prompted weak supervision (PromptedWS) applies pre-trained large language models (LLMs) as the basis for labeling functions (LFs) in a weak supervision framework to obtain large labeled datasets. We further extend the us…

MemeScouts@LT-EDI 2026: Asking the Right Questions -- Prompted Weak Supervision for Meme Hate Speech Detection

2026-04-27 · Ivo Bueno, Lea Hirlimann, Enkelejda Kasneci arxiv

Detecting hate speech in memes is challenging due to their multimodal nature and subtle, culturally grounded cues such as sarcasm and context. While recent vision-language models (VLMs) enable joint reasoning over text a…

Hate Speech Detection

Weak Supervision in Analysis of News: Application to Economic Policy Uncertainty

2022-08-10 · Paul Trust, Ahmed Zahran, Rosane Minghim

The need for timely data analysis for economic decisions has prompted most economists and policy makers to search for non-traditional supplementary sources of data. In that context, text data is being explored to enrich …

Articles

Weakly Supervised Veracity Classification with LLM-Predicted Credibility Signals

2023-09-14 · João A. Leite, Olesya Razuvayevskaya, Kalina Bontcheva, Carolina Scarton

Credibility signals represent a wide range of heuristics typically used by journalists and fact-checkers to assess the veracity of online content. Automating the extraction of credibility signals presents significant cha…

MisinformationVeracity Classification

DialFRED: Dialogue-Enabled Agents for Embodied Instruction Following

2022-02-27 · Xiaofeng Gao, Qiaozi Gao, Ran Gong, Kaixiang Lin 외

Language-guided Embodied AI benchmarks requiring an agent to navigate an environment and manipulate objects typically allow one-way communication: the human user gives a natural language command to the agent, and the age…

Instruction FollowingNavigate