Related papers: ImplicitBBQ: Benchmarking Implicit Bias in Large L…
This paper addresses the issue of implicit stereotypes that may arise during the generation process of large language models. It proposes an interpretable bias detection method aimed at identifying hidden social biases in model outputs,…
With the widespread adoption of Large Language Models (LLMs) across various applications, it is empirical to ensure their fairness across all user communities. However, most LLMs are trained and evaluated on Western centric data, with…
Evaluating social biases in language models (LMs) is crucial for ensuring fairness and minimizing the reinforcement of harmful stereotypes in AI systems. Existing benchmarks, such as the Bias Benchmark for Question Answering (BBQ),…
Large Language models (LLMs), such as ChatGPT, have gained popularity in recent years with the advancement of Natural Language Processing (NLP), with use cases spanning many disciplines and daily lives as well. LLMs inherit explicit and…
Large Language Models (LLMs) are increasingly integral to information dissemination and decision-making processes. Given their growing societal influence, understanding potential biases, particularly within the political domain, is crucial…
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 implicit rather than…
This paper investigates the subtle and often concealed biases present in Large Language Models (LLMs), focusing on implicit biases that may remain despite passing explicit bias tests. Implicit biases are significant because they influence…
While various approaches have recently been studied for bias identification, little is known about how implicit language that does not explicitly convey a viewpoint affects bias amplification in large language models. To examine the…
While advances in fairness and alignment have helped mitigate overt biases exhibited by large language models (LLMs) when explicitly prompted, we hypothesize that these models may still exhibit implicit biases when simulating human…
With natural language generation becoming a popular use case for language models, the Bias Benchmark for Question-Answering (BBQ) has grown to be an important benchmark format for evaluating stereotypical associations exhibited by…
Due to the implement of guardrails by developers, Large language models (LLMs) have demonstrated exceptional performance in explicit bias tests. However, bias in LLMs may occur not only explicitly, but also implicitly, much like humans who…
As generative large language models (LLMs) grow more performant and prevalent, we must develop comprehensive enough tools to measure and improve their fairness. Different prompt-based datasets can be used to measure social bias across…
Large Language Models (LLMs) are being adopted across a wide range of tasks, including decision-making processes in industries where bias in AI systems is a significant concern. Recent research indicates that LLMs can harbor implicit biases…
Safety-aligned large language models (LLMs) are becoming increasingly widespread, especially in sensitive applications where fairness is essential and biased outputs can cause significant harm. However, evaluating the fairness of models is…
Previous literature has largely shown that Large Language Models (LLMs) perpetuate social biases learnt from their pre-training data. Given the notable lack of resources for social bias evaluation in languages other than English, and for…
With the development of large language models (LLMs), social biases in these LLMs have become a pressing issue. Although there are various benchmarks for social biases across languages, the extent to which Japanese LLMs exhibit social…
We investigate how LLMs encode sociodemographic attributes of human conversational partners inferred from indirect cues such as names and occupations. We show that LLMs develop linear representations of user demographics within activation…
A dangerous assumption that can be made from prior work on the bias transfer hypothesis (BTH) is that biases do not transfer from pre-trained large language models (LLMs) to adapted models. We invalidate this assumption by studying the BTH…
Recent work has indicated that many natural language understanding and reasoning datasets contain statistical cues that may be taken advantaged of by NLP models whose capability may thus be grossly overestimated. To discover the potential…
Large language models (LLMs), despite their remarkable capabilities, are susceptible to generating biased and discriminatory responses. As LLMs increasingly influence high-stakes decision-making (e.g., hiring and healthcare), mitigating…