Track new results across pure and applied mathematics.
Search papers, labs, and topics across Lattice.
This paper introduces STEREODISCO, a novel framework that systematically investigates stereotypical associations in large language models (LLMs) by adapting the semantic differential method to probe their internal representations. By constructing approximately 2,000 candidate semantic axes from WordNet antonym synsets and applying statistical tests on concept projections, the authors reveal that LLMs like LLAMA-3-8B-INSTRUCT and MISTRAL-7B-INSTRUCT exhibit agreement on social group stereotypes that diverges from established social psychology findings. Notably, the study uncovers new stereotypical axes, such as humble vs. proud and narrow-minded vs. broad-minded, which are validated by human annotators, highlighting the complex nature of stereotype encoding in LLMs.
LLMs may encode stereotypes in ways that significantly diverge from human perceptions, revealing new axes of stereotypicality that challenge existing social psychology frameworks.
LLMs encode, convey, and perpetuate stereotypes. Prior computational research focuses on a small set of semantic axes investigated in social psychology, and operates on word embeddings produced by language models, leaving open which other semantic axes carry stereotypical associations in LLMs and how LLMs internally represent such axes. We introduce STEREODISCO, a framework that adapts the semantic differential method (Osgood et al., 1957) to the systematic study of stereotypes in LLM internal representations. STEREODISCO constructs approx. 2,000 candidate semantic axes from WordNet antonym synsets, recovers each as a geometric axis in the LLM's activation space via probing, and identifies stereotypical axes via a statistical test over concept projections. As a case study, we apply STEREODISCO to social group stereotypes with LLAMA-3-8B-INSTRUCT and MISTRAL-7B-INSTRUCT. We find that the two LLMs agree with each other on social group ratings more than with humans, suggesting that LLM-encoded stereotype content diverges from that documented in social psychology. We also discover stereotypical axes not investigated in prior work -- including humble vs. proud, narrow-minded vs. broad-minded, and cowardly vs. brave, which human annotators independently confirm.