paper-with-me

홈 › Papers

Societal Biases in Language Generation: Progress and Challenges

2021-05-10 · ACL 2021 5 · Emily Sheng, Kai-Wei Chang, Premkumar Natarajan, Nanyun Peng

Technology for language generation has advanced rapidly, spurred by advancements in pre-training large models on massive amounts of data and the need for intelligent agents to communicate in a natural manner. While techniques can effectively generate fluent text, they can also produce undesirable societal biases that can have a disproportionately negative impact on marginalized populations. Language generation presents unique challenges for biases in terms of direct user interaction and the structure of decoding techniques. To better understand these challenges, we present a survey on societal biases in language generation, focusing on how data and techniques contribute to biases and progress towards reducing biases. Motivated by a lack of studies on biases from decoding techniques, we also conduct experiments to quantify the effects of these techniques. By further discussing general trends and open challenges, we call to attention promising directions for research and the importance of fairness and inclusivity considerations for language generation applications.

📄 PDF Abstract BibTeX arXiv:2105.04054

Code (1)

ewsheng/decoding-biases 공식 구현

Tasks

FairnessText Generation

Similar Papers 제목 키워드 기반

Investigating Societal Biases in a Poetry Composition System

2020-11-05 · GeBNLP (COLING) 2020 12 · Emily Sheng, David Uthus

There is a growing collection of work analyzing and mitigating societal biases in language understanding, generation, and retrieval tasks, though examining biases in creative tasks remains underexplored. Creative languag…

Data AugmentationRetrievalStyle Transfer

Towards Controllable Biases in Language Generation

2020-05-01 · Findings of the Association for Computational Linguistics 2020 · Emily Sheng, Kai-Wei Chang, Premkumar Natarajan, Nanyun Peng

We present a general approach towards controllable societal biases in natural language generation (NLG). Building upon the idea of adversarial triggers, we develop a method to induce societal biases in generated text whe…

Dialogue GenerationText Generation

Uncovering Biases with Reflective Large Language Models

2024-08-24 · Edward Y. Chang

Biases and errors in human-labeled data present significant challenges for machine learning, especially in supervised learning reliant on potentially flawed ground truth data. These flaws, including diagnostic errors and…

Bias DetectionDiagnostic

Disability Representations: Finding Biases in Automatic Image Generation

2024-06-21 · Yannis Tevissen

Recent advancements in image generation technology have enabled widespread access to AI-generated imagery, prominently used in advertising, entertainment, and progressively in every form of visual content. However, these…

Image Generation

Fine-Tuned LLMs are "Time Capsules" for Tracking Societal Bias Through Books

2025-02-07 · Sangmitra Madhusudan, Robert Morabito, Skye Reid, Nikta Gohari Sadr 외

Books, while often rich in cultural insights, can also mirror societal biases of their eras - biases that Large Language Models (LLMs) may learn and perpetuate during training. We introduce a novel method to trace and qu…