arXiv AI
Unfair and Unsafe: Everyday Bias Triggers Emergent Misalignment
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Sep 2
BiasGym: A Simple and Generalizable Framework for Analyzing and Removing Biases through Injection
BiasGym is a cost‑effective, generalizable framework that injects specific biases into large language models via token‑based fine‑tuning while keeping the model frozen. It then uses two debiasing methods—Scope and Steer—to identify and suppress or redirect the components responsible for biased behavior. The framework enables consistent bias elicitation, precise localization of bias associations, and targeted debiasing without harming downstream performance, and it has been shown to reduce real‑world stereotypes such as labeling Italians as reckless drivers.
arXiv Computation and Language
Sep 2
Evaluating Second-Order Bias of LLMs Through Epistemic Entitlement
The paper introduces a novel framework for assessing second‑order bias in large language models (LLMs), defined as bias in how an LLM judges the acceptability of biased content. Using principles from entitlement epistemology, the authors design a reasoning task that asks LLMs to determine whether a biased text is acceptable for specific demographic groups, and propose two metrics to quantify biased judgments. Experiments on both open‑source and closed‑source models reveal that the task bypasses safety guardrails, uncovers systematic variations across target groups, and demonstrates that models still rely on demographic labels when evaluating bias.
arXiv AI
Aug 13
Large Language Models Reproduce Racial Stereotypes When Used for Text Annotation
arXiv:2603. 13891v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly used for automated text annotation in tasks ranging from academic research to content moderation and hiring.
Hugging Face Trending Papers
Jun 17
The Wrong Kind of Right: Quantifying and Localizing Misfired Alignment in LLMs
Warning: This paper studies stereotypes and biases, and contains potentially disturbing examples, used for illustration purposes only. Our findings should not be interpreted as an argument against alignment.
arXiv AI
Jul 17
Innocuous-Seeming Data, Latent Ideology: Ideological Generalisation in Finetuned LLMs
arXiv:2607. 14888v1 Announce Type: cross Abstract: Finetuning language models on small, curated datasets is standard practice for adapting them to specific policies or domains.
arXiv AI
Sep 1
Benevolent Bias in Multi-Turn Human-Agent Dialogue
arXiv:2608.29206v1 Announce Type: new Abstract: Bias in human-agent interaction can manifest not only through hostile language but also as benevolent bias, whereby unequal treatment hides behind a wa...