arXiv subjects

Hazel Chen

Publications and source records attributed to Hazel Chen.

2 recordsLinked to original sources

arXiv2026

Guilt by Association: Semantic Leakage Drives Associative Gender Bias

Semantic leakage occurs when a concept in the prompt steers model generation about an entity, even though the concept is irrelevant to it (e.g., a person who likes yellow is said to work as a school bus driver). It has mostly been studied in settings where the concept is directly attributed to the entity the model is asked about. This leaves open whether leakage is a flawed heuristic, where the model builds a profile of that entity, or a much broader associative tendency, e.g., working across seemingly unrelated entities. We argue for the latter: even after removing the attribution of the concept to the specific entity, leakage persists. Next, we extend this idea to gender bias. While work on gender bias in LMs typically looks at cases where the stereotyped concept is attributed to an entity, our findings suggest that a concept may steer outputs with its mere presence in the scene. We show this using gendered concepts under two conditions: when the subject engages with the concept, and when the concept just sits in the scene. We find that both shift model generation toward the stereotype to a similar extent. Together, our results suggest that semantic leakage drives a form of bias that is overlooked by current evaluations.

cs.CL↗

arXiv2026

Is Convergence Inevitable? Tracing Output Homogeneity Back to Base Models

The lack of diversity in LM content is widely attributed to the alignment process, but how and where exactly in the pipeline this collapse begins is unknown. We argue that output homogeneity is likely learned during the pretraining phase, and only revealed or magnified during the alignment process. Specifically, we find that semantic convergence is observed from the first alignment stage--the instruction-tuning phase (SFT)--suggesting that homogeneity might already exist in the pre-alignment model. To investigate this, we conduct controlled SFT experiments examining how training data influences output convergence on specific input/output pairs. We find that convergence can be revealed and amplified, but not introduced by the SFT data, supporting its role as a catalyst rather than a cause. To further test whether homogeneity originates before alignment, we measure convergence in base models. We find that instruct-like collapse can be induced through prompting alone, even without alignment. Taken together, our results suggest that semantic convergence may arise naturally from the objectives underlying LM training, making it difficult to mitigate through post-alignment interventions alone.

cs.CL↗