Evaluating the Effect of Retrieval Augmentation on Social Biases
Retrieval Augmented Generation (RAG) has gained popularity as a method for conveniently incorporating novel facts that were not seen during the pre-training stage in Large Language Model (LLM)-based Natural Language Generation (NLG) systems. However, LLMs are known to encode significant levels of unfair social biases. The modulation of these biases by RAG in NLG systems is not well understood. In this paper, we systematically study the relationship between the different components of a RAG system and the social biases presented in the text generated across three languages (i.e. English, Japanese and Chinese) and four social bias types (i.e. gender, race, age and religion). Specifically, using the Bias Question Answering (BBQ) benchmark datasets, we evaluate the social biases in RAG responses from document collections with varying levels of stereotypical biases, employing multiple LLMs used as generators. We find that the biases in document collections are often amplified in the generated responses, even when the generating LLM exhibits a low-level of bias. Our findings raise concerns about the use of RAG as a technique for injecting novel facts into NLG systems and call for careful evaluation of potential social biases in RAG applications before their real-world deployment.
Code (0)
등록된 구현이 없습니다.
Tasks
Large Language ModelQuestion AnsweringRAGRetrievalRetrieval-augmented GenerationText GenerationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Sense Embeddings are also Biased--Evaluating Social Biases in Static and Contextualised Sense Embeddings
Sense embedding learning methods learn different embeddings for the different senses of an ambiguous word. One sense of an ambiguous word might be socially biased while its other senses remain unbiased. In comparison to …
Word EmbeddingsSense Embeddings are also Biased – Evaluating Social Biases in Static and Contextualised Sense Embeddings
Sense embedding learning methods learn different embeddings for the different senses of an ambiguous word. One sense of an ambiguous word might be socially biased while its other senses remain unbiased. In comparison to …
Word EmbeddingsSense Embeddings are also Biased -- Evaluating Social Biases in Static and Contextualised Sense Embeddings
Sense embedding learning methods learn different embeddings for the different senses of an ambiguous word. One sense of an ambiguous word might be socially biased while its other senses remain unbiased. In comparison to …
Word EmbeddingsIdentifying Implicit Social Biases in Vision-Language Models
Vision-language models, like CLIP (Contrastive Language Image Pretraining), are becoming increasingly popular for a wide range of multimodal retrieval tasks. However, prior work has shown that large language and deep vis…
FairnessA word association network methodology for evaluating implicit biases in LLMs compared to humans
As Large language models (LLMs) become increasingly integrated into our lives, their inherent social biases remain a pressing concern. Detecting and evaluating these biases can be challenging because they are often impli…