Evaluate Bias without Manual Test Sets: A Concept Representation Perspective for LLMs
Journal:
arXiv
Published Date:
May 21, 2025
Abstract
Bias in Large Language Models (LLMs) significantly undermines their
reliability and fairness. We focus on a common form of bias: when two reference
concepts in the model's concept space, such as sentiment polarities (e.g.,
"positive" and "negative"), are asymmetrically correlated with a third, target
concept, such as a reviewing aspect, the model exhibits unintended bias. For
instance, the understanding of "food" should not skew toward any particular
sentiment. Existing bias evaluation methods assess behavioral differences of
LLMs by constructing labeled data for different social groups and measuring
model responses across them, a process that requires substantial human effort
and captures only a limited set of social concepts. To overcome these
limitations, we propose BiasLens, a test-set-free bias analysis framework based
on the structure of the model's vector space. BiasLens combines Concept
Activation Vectors (CAVs) with Sparse Autoencoders (SAEs) to extract
interpretable concept representations, and quantifies bias by measuring the
variation in representational similarity between the target concept and each of
the reference concepts. Even without labeled data, BiasLens shows strong
agreement with traditional bias evaluation metrics (Spearman correlation r >
0.85). Moreover, BiasLens reveals forms of bias that are difficult to detect
using existing methods. For example, in simulated clinical scenarios, a
patient's insurance status can cause the LLM to produce biased diagnostic
assessments. Overall, BiasLens offers a scalable, interpretable, and efficient
paradigm for bias discovery, paving the way for improving fairness and
transparency in LLMs.
