arXiv:2501. 14844v3 Announce Type: replace-cross Abstract: Detecting biases in the outputs produced by generative models is essential to reduce the potential risks associated with their application in critical settings.
arXiv:2602. 04306v2 Announce Type: replace-cross Abstract: As large language models (LLMs) are increasingly deployed in real-world applications, ensuring their fair responses across demographics has become crucial.
arXiv:2609.13579v1 Announce Type: new Abstract: Safety research often focuses on model-generated harms, but users may also direct hostility, coercion, and adversarial pressure at models. Understandin...
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:2609.18649v1 Announce Type: new Abstract: Warning: This paper contains examples of stereotypes and social bias. LLMs are increasingly used in interactive settings by the general public, making...
The paper introduces a counterfactually anchored evidence attribution approach for multi‑turn large language model safety failures. It presents a new dataset of 1,762 conversations, including adversarial, benign twins, and high‑risk vocabulary variants, and trains a lightweight hierarchical model that accurately predicts safety violations and attributes them to specific user turns and token spans. The model achieves high detection performance (F1 = 0.988) and significantly reduces adversarial confidence when top‑attributed tokens are removed, while maintaining low false‑positive rates on benign conversations.
The paper introduces GPTBIAS, a framework that uses powerful large language models like GPT‑4 to evaluate bias in other LLMs. It employs specially crafted prompts called Bias Attack Instructions to probe for bias and outputs a bias score along with detailed information such as bias types, affected demographics, keywords, reasons, and improvement suggestions. Extensive experiments demonstrate the framework’s effectiveness and usability.
Large language models (LLMs) are increasingly used to assess social bias in text, but the passages they evaluate often contain surface noise such as typos and broken punctuation. This study applied five realistic noise conditions at varying intensities to 3,822 stereotype‑related responses and compared bias judgments on noisy versus original text. The findings show that noise disproportionately turns neutral judgments into biased ones—up to 120 times more likely—while rarely converting biased judgments into neutral ones, and that the most fragile LLM judge exhibits the greatest distortion at mild noise levels. As LLMs become more robust, the bias distortion tends toward parity rather than reversal, meaning bias measured on noisy text is systematically overestimated, especially in fairness‑critical categories.
The paper evaluates the use of large language models (LLMs) as judges for assessing conversational voice agents, comparing human judgments with GPT‑4.1 and GPT‑5 across telecom and retail interactions. It examines agreement, metric‑level correlations, and consistency across three evaluation configurations (p0, p1, p2) to determine how reliably LLMs can judge conversational quality and safety. The study finds that LLM‑based evaluation can be effective but its reliability varies by metric and configuration, suggesting a hybrid approach where LLMs handle scalable assessment while humans focus on metrics requiring contextual interpretation.
Large Language Models (LLMs) as judges across various scenarios such as assessing model responses is becoming an increasingly accepted paradigm. However, existing judgment approaches often rely on trained judgers using fixed preference data, which tend to overlook diverse user preferences and struggle to adapt to real-world human-AI dialogue scenarios.
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:2609.38964v1 Announce Type: new Abstract: Multi-agent debate (MAD) is often used to improve large language model (LLM) reasoning, but sequential debate is rarely a neutral aggregator of agents'...