CFL: Causally Fair Language Models Through Token-level Attribute Controlled Generation
We propose a method to control the attributes of Language Models (LMs) for the text generation task using Causal Average Treatment Effect (ATE) scores and counterfactual augmentation. We explore this method, in the context of LM detoxification, and propose the Causally Fair Language (CFL) architecture for detoxifying pre-trained LMs in a plug-and-play manner. Our architecture is based on a Structural Causal Model (SCM) that is mathematically transparent and computationally efficient as compared with many existing detoxification techniques. We also propose several new metrics that aim to better understand the behaviour of LMs in the context of toxic text generation. Further, we achieve state of the art performance for toxic degeneration, which are computed using \RTP (RTP) benchmark. Our experiments show that CFL achieves such a detoxification without much impact on the model perplexity. We also show that CFL mitigates the unintended bias problem through experiments on the BOLD dataset.
Code (0)
등록된 구현이 없습니다.
Tasks
AttributecounterfactualText GenerationSimilar Papers 제목 키워드 기반
Causally Perturbed Fairness Testing
To mitigate unfair and unethical discrimination over sensitive features (e.g., gender, age, or race), fairness testing plays an integral role in engineering systems that leverage AI models to handle tabular data. A key c…
Causal InferenceHow Do Language Models Represent and Use Phonological Information for Allomorph Selection?
Language models are trained on tokenized text that obscures the sound structure of words, yet they reliably produce morphemes whose form is phonologically conditioned. It remains unclear whether they rely on item-specifi…
A Mechanistic Understanding of Pronoun Fidelity in LLMs
Faithful and robust pronoun use is important for fair and coherent generations, yet large language models largely fail when multiple referents use different pronouns. To study the interplay of reasoning, repetition, and …
A pipeline for enabling path-specific causal fairness in observational health data
When training machine learning (ML) models for potential deployment in a healthcare setting, it is essential to ensure that they do not replicate or exacerbate existing healthcare biases. Although many definitions of fai…
Process-Supervised LLM Recommenders via Flow-guided Tuning
While large language models (LLMs) are increasingly adapted for recommendation systems via supervised fine-tuning (SFT), this approach amplifies popularity bias due to its likelihood maximization objective, compromising …
DiversityFairnessRecommendation Systems