DeepBias: Adaptive In-depth Probing of Social Biases in LVLMs

• URL: http://arxiv.org/abs/2607.11228v1
• Date: Mon, 13 Jul 2026 08:19:09 GMT
• Title: DeepBias: Adaptive In-depth Probing of Social Biases in LVLMs
• Abstract summary: We introduce DeepBias, an adaptive framework for the in-depth probing of social biases in LVLMs with carefully designed agents.<n>We build a benchmark named DeepBiasBench using our framework. By employing an ensemble of five diverse state-of-the-art LVLMs as anchors, the benchmark captures vulnerabilities shared across architectures.
• Score: 71.85279836937578
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: While Large Vision-Language Models (LVLMs) demonstrate remarkable capabilities, they remain highly susceptible to embedded social biases. Existing bias evaluation protocols predominantly rely on static datasets, which provide only a superficial assessment, as their fixed test cases cannot adaptively evolve to measure the true depth and limits of model vulnerabilities. We introduce DeepBias, an adaptive framework for the in-depth probing of social biases in LVLMs with carefully designed agents. Our approach operates through a dynamic ''generation-evolution-probing'' loop. First, a generative ProposerAgent synthesizes test data and is iteratively updated via Direct Preference Optimization (DPO) based on the target LVLM's responses, exploring model-specific failure modes. Second, an autonomous skill-driven DiggerAgent rewrites each test data across multiple probing turns, adaptively selecting from a curated skill library of deepening and rewriting strategies. At each turn, this process is conditioned on the model's previous response, enabling progressively deeper biases to be exposed. Furthermore, we build a benchmark named DeepBiasBench using our framework. By employing an ensemble of five diverse state-of-the-art LVLMs as anchors, the benchmark captures vulnerabilities shared across architectures. Comprehensive experiments demonstrate the effectiveness of our framework and show that DeepBias provides a challenging benchmark for in-depth bias evaluation, establishing an evolutionary paradigm for LVLM safety assessment.

Related papers

• Be Your Own Teacher: Steering Protein Language Models via Unsupervised Reward Optimization [85.4863852505905]
  We introduce unsupervised reward optimization of protein language models (PLMs)<n>Our key insight is that task-agnostic rewards, which combine intrinsic model uncertainty with semantic consistency informed by protein representation models, exhibit strong correlation with controllability measures across base models and temperature regimes.<n>Our framework provides a scalable pathway toward controllable biomolecular design in settings where labeled preferences or experimental feedback are scarce or unavailable.
  arXiv  Detail & Related papers  (2026-06-17T11:42:01Z)
• Dual-Teacher Distillation with Subnetwork Rectification for Black-Box Domain Adaptation [69.7036779439312]
  Black box domain adaptation represents a highly practical yet extremely challenging setting.<n>We propose a dual teacher distillation with subnetwork rectification (DDSR) model that exploits specific knowledge embedded in black box source models.<n>Our approach demonstrates consistent improvements over state of the art methods, including those using source data or models.
  arXiv  Detail & Related papers  (2026-03-24T07:54:19Z)
• VULPO: Context-Aware Vulnerability Detection via On-Policy LLM Optimization [2.6678231901651723]
  This paper introduces Vulnerability-Adaptive Policy Optimization (VULPO), an on-policy LLM reinforcement learning framework for context-aware vulnerability detection.<n>To support training and evaluation, we first construct ContextVul, a new dataset that augments high-quality function-level samples with lightweight method to extract repository-level context information.<n>To address the asymmetric difficulty of different vulnerability cases and mitigate reward hacking, VULPO incorporates label-level and sample-level difficulty-adaptive reward scaling.
  arXiv  Detail & Related papers  (2025-11-14T21:57:48Z)
• RECALL: REpresentation-aligned Catastrophic-forgetting ALLeviation via Hierarchical Model Merging [33.22889542330089]
  Internal representations in large language models (LLMs) serve as reliable proxies of learned knowledge.<n>We propose RECALL, a representation-aware model merging framework for continual learning without access to historical data.
  arXiv  Detail & Related papers  (2025-10-23T12:17:37Z)
• Self-Evolutionary Large Language Models through Uncertainty-Enhanced Preference Optimization [9.618391485742968]
  Iterative preference optimization has recently become one of the de-facto training paradigms for large language models (LLMs) We present an uncertainty-enhanced textbfPreference textbfOptimization framework to make the LLM self-evolve with reliable feedback. Our framework substantially alleviates the noisy problem and improves the performance of iterative preference optimization.
  arXiv  Detail & Related papers  (2024-09-17T14:05:58Z)
• Self-Augmented Preference Optimization: Off-Policy Paradigms for Language Model Alignment [104.18002641195442]
  We introduce Self-Augmented Preference Optimization (SAPO), an effective and scalable training paradigm that does not require existing paired data. Building on the self-play concept, which autonomously generates negative responses, we further incorporate an off-policy learning pipeline to enhance data exploration and exploitation.
  arXiv  Detail & Related papers  (2024-05-31T14:21:04Z)
• Self-Exploring Language Models: Active Preference Elicitation for Online Alignment [88.56809269990625]
  We propose a bilevel objective optimistically biased towards potentially high-reward responses to actively explore out-of-distribution regions. Our experimental results demonstrate that when fine-tuned on Zephyr-7B-SFT and Llama-3-8B-Instruct models, Self-Exploring Language Models (SELM) significantly boosts the performance on instruction-following benchmarks.
  arXiv  Detail & Related papers  (2024-05-29T17:59:07Z)
• Automating Dataset Updates Towards Reliable and Timely Evaluation of Large Language Models [81.27391252152199]
  Large language models (LLMs) have achieved impressive performance across various natural language benchmarks. We propose to automate dataset updating and provide systematic analysis regarding its effectiveness. There are two updating strategies: 1) mimicking strategy to generate similar samples based on original data, and 2) extending strategy that further expands existing samples.
  arXiv  Detail & Related papers  (2024-02-19T07:15:59Z)
• A Conditioned Unsupervised Regression Framework Attuned to the Dynamic Nature of Data Streams [0.0]
  This paper presents an optimal strategy for streaming contexts with limited labeled data, introducing an adaptive technique for unsupervised regression. The proposed method leverages a sparse set of initial labels and introduces an innovative drift detection mechanism. To enhance adaptability, we integrate the ADWIN (ADaptive WINdowing) algorithm with error generalization based on Root Mean Square Error (RMSE)
  arXiv  Detail & Related papers  (2023-12-12T19:23:54Z)
• Consistency Regularization for Generalizable Source-free Domain Adaptation [62.654883736925456]
  Source-free domain adaptation (SFDA) aims to adapt a well-trained source model to an unlabelled target domain without accessing the source dataset. Existing SFDA methods ONLY assess their adapted models on the target training set, neglecting the data from unseen but identically distributed testing sets. We propose a consistency regularization framework to develop a more generalizable SFDA method.
  arXiv  Detail & Related papers  (2023-08-03T07:45:53Z)
• Beyond Deep Ensembles: A Large-Scale Evaluation of Bayesian Deep Learning under Distribution Shift [19.945634052291542]
  We evaluate modern BDL algorithms on real-world datasets from the WILDS collection containing challenging classification and regression tasks. We compare the algorithms on a wide range of large, convolutional and transformer-based neural network architectures. We provide the first systematic evaluation of BDL for fine-tuning large pre-trained models.
  arXiv  Detail & Related papers  (2023-06-21T14:36:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.