The paper investigates how large language models (LLMs) from OpenAI and Anthropic exhibit probability bias when deciding whether to trust information from reporters of different racial descriptions. Using a two‑urn Bayesian game and 6,600 sessions, the authors find that models often refuse to assess a reporter’s credibility—especially for Black‑described reporters—yet when they do assess, Black reporters receive slightly higher trust. The bias is subtle, growing with reasoning effort, and is not detected by standard audits that compare average trust or only assessed cases.
Almost every large language model that reaches a broad audience is quantized: trained in full precision, then compressed for efficiency. This step is assumed harmless and its safety is rarely re-checked.
The paper examines how automated safety systems unevenly flag harmful content, disproportionately labeling African American English as offensive and misclassifying content from drag queens and white nationalists. It identifies seven failure modes rooted in vocabulary-based harm detection and proposes an evaluation protocol that highlights gaps in performance across languages. Applied to five open systems in eleven languages, the study finds that none achieve native-speaker accuracy, and higher capability often increases discrimination, widening the disparity between best- and worst-served language communities.
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:2608. 07762v1 Announce Type: new Abstract: LLM benchmarks can build an organization's reputation and attract customers, but only when results are transparent and verifiable.
arXiv:2610.15961v1 Announce Type: cross Abstract: Emergent misalignment (EM) occurs when fine-tuning a language model to a narrow task makes it misaligned on unrelated ones. Because organizations now...
arXiv:2609.00222v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used as judges for subjective tasks, where annotators disagree and the relevant question is not only how...
arXiv:2606. 32008v1 Announce Type: new Abstract: Mechanistic interpretability (MI) requires full access to model internals, yet the APIs for most widely deployed language models at best expose log-probabilities over output tokens.
The paper examines whether removing declared language fields from de‑identified résumés eliminates demographic leakage in large language models. By keeping language attributes identical and varying only unstructured prose across five ethnocultural groups and three cue‑salience levels, the authors find that non‑language text still allows target‑group recovery (average 0.757, reaching 1.000 under high salience). They also show that evaluation design—such as allowing or forbidding ties—dramatically affects LLM‑as‑a‑judge outcomes, underscoring the importance of evaluation protocol in bias audits.
The paper demonstrates that large language model (LLM) evaluators, whether reward‑model based or prompted LLM‑as‑a‑Judge, exhibit significant language bias in multilingual settings. Experiments with semantically identical instruction‑response pairs across 23 languages reveal that lower‑resource languages receive higher scores, a bias that persists across eight open‑weight evaluators and is not detectable by standard pairwise accuracy metrics. The authors link the bias to model uncertainty and language identity, showing it cannot be explained by content difficulty alone.
arXiv:2608.18768v2 Announce Type: replace Abstract: Large language models are widely used to simulate survey respondents, yet their outputs are homogeneous and unfaithful to real inter-group differen...
arXiv:2608.29590v1 Announce Type: new Abstract: We propose a societal bias evaluation method for large vision-language models (LVLMs) in the era of strong safety guardrails. Existing benchmarks rely...
The paper reports the first systematic audit of open‑weight large language models (LLMs) in hiring contexts, examining how job‑posting language influences recruiter and job‑seeker simulations across six models. It finds that agentic language lowers recruiter scores for female candidates while communal language mitigates this effect, and that coded‑exclusion language sharply reduces recruiter scores for non‑White candidates and discourages non‑White personas from applying. The study also identifies the explicit demographic label as the main causal factor and proposes a concrete pre‑deployment audit protocol aligned with EU and U.S. regulatory requirements.