The paper introduces DeLask, a novel decoding framework that dynamically skips or partially aggregates problematic decoder layers to significantly mitigate hallucinations in Large Language Models.

This paper systematically analyzes how different architectural components of Large Vision-Language Models (LVLMs) contribute to hallucination robustness, finding that joint enhancement of visual fidel…

The paper proposes In-Context Visual Contrastive Optimization (IC-VCO) to rigorously mitigate multimodal hallucinations in Vision-Language Models by optimizing contrastive learning within a shared mul…

The paper introduces Responsible Contrastive Soft Prompting (RCSP), a parameter-efficient method using soft prompts to improve LLM reliability by simultaneously suppressing hallucinations, encouraging…

The paper proposes Visual Gradient Steering (VGS), a method that decomposes the distillation loss into language and visual components and steers the optimization to prioritize visual grounding, signif…

The paper proposes Resonant Context Anchoring (RCA), a lightweight, training-free method that enhances factual faithfulness in LLMs by dynamically amplifying the signal of external context evidence du…

The paper proposes Reasoning-Conditioned Direct Preference Optimization (RC-DPO) to effectively mitigate hallucinations in multimodal large reasoning models by explicitly conditioning the preference o…

The paper introduces REALISTA, a novel latent-space adversarial attack framework that generates semantically realistic and coherent prompts to effectively induce hallucinations in large language model…

TriLens is a white-box detector that monitors the entropy of three internal streams (attention, feed-forward, residual) at every layer of a language model to detect hallucinations by tracking how inte…

The paper analyzes token reduction for efficient unified VLM training, finding that while task-specific acceleration saves computation, it destroys the mutual performance gains achieved through joint…

肖代替了视觉令牌的永久删除，通过可恢复的路由来改进视觉语言模型的性能

The paper introduces LL-Bench, a comprehensive benchmark for evaluating large-scale generative models on low-level vision tasks, and proposes LL-Score, an MLLM-based evaluator that better aligns quali…

MASER is a lightweight framework that dynamically routes a shared Vision-Language Model (VLM) to the most appropriate modality-specific adapter (e.g., point cloud, RGB) based on the input question, si…

The paper introduces BenHalluEval, the first dedicated multi-task framework for systematically evaluating hallucination in Large Language Models (LLMs) specifically for the Bengali language.

The paper proposes CTRL-STEER, a closed-loop framework that adaptively adjusts intervention strength to stabilize concept regulation and improve task success in Vision-Language-Action models without r…

The paper introduces CrossMPI, a novel cross-modal prompt injection attack that uses image-only perturbations to steer the interpretation of both textual and visual inputs in Large Vision-Language Mod…

The paper introduces Evidence-Carrying Agents (ECA) to prevent multimodal agents from executing privileged actions based on unsupported or hallucinated perceptual claims, achieving near-zero unsafe ex…

The paper proposes a memory-augmented, three-stage agentic pipeline that significantly reduces LLM hallucinations and improves operational efficiency by integrating semantic caching and advanced obser…

The paper introduces Adaptive Unlearning (AU), a post-deployment framework that surgically suppresses code-related hallucinations, significantly reducing the risk of package confusion attacks like slo…