arXiv AI
Aug 7
Seeing Is Not Deciding: Can Multimodal LLMs Act as Effective CEOs?
arXiv:2608. 05864v1 Announce Type: new Abstract: Large language models are increasingly applied as autonomous decision-making agents.
Seeing Is Not Deciding: Can Multimodal LLMs Act as Effective CEOs?
Large language models are increasingly applied as autonomous decision-making agents. However, in executive business decisions, existing benchmarks are limited to textonly settings.
Related stories
arXiv AI
Aug 26
Seeing vs. Believing: Evaluating the Language Bias of Open-Source MLLMs in Counter-Intuitive Scenes
The paper introduces CAIT, a benchmark of 400 synthetic scenes featuring counter‑intuitive actions that challenge multimodal large language models (MLLMs). Human participants and proprietary models like Claude and Gemini perform well, but standard open‑source instruction‑tuned MLLMs fail, largely due to a strong language prior that overrides contradictory visual evidence. The study shows that Chain‑of‑Thought reasoning can help but introduces new issues, while targeted fine‑tuning and structured prompting can reduce reliance on language priors and improve visual grounding.
arXiv AI
Aug 17
BUZZY: Contrastive Scoring to Mitigate Text-Induced Bias in Multimodal Multiple-Choice QA
arXiv:2603. 28026v2 Announce Type: replace Abstract: Multimodal multiple-choice question answering (MCQA) provides a standardized and objectively measurable setting for evaluating vision-language models (VLMs).
arXiv Computation and Language
Aug 21
When Irrelevant Text Matters: Affine Margin Shifts in Multimodal Large Language Models
arXiv:2608. 19208v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) are frequently exposed to auxiliary textual context, the impact of which on visually grounded tasks remains underexplored.
arXiv Computation and Language
Sep 7
From Vision to Language: Investigating Causal Information Flow in Multimodal Decision-Making
The study examines how Vision‑Language Models (VLMs) integrate visual evidence into language‑based decisions by applying layer‑wise causal interventions on video‑text attention pathways in a video‑based generative multiple‑choice setting. Findings reveal that visual information is primarily incorporated while processing candidate answer options, with nouns serving as key semantic anchors and verbs becoming important during temporal reasoning. The research also uncovers a distinct pattern in temporal reasoning, indicating that VLMs struggle to reconstruct sequential information across video frames, possibly due to linguistic biases in temporal expressions.
arXiv AI
Jul 31
See2Think: Do Multimodal Models Really Use Intermediate Visual States?
arXiv:2607. 26769v1 Announce Type: cross Abstract: Multimodal large language models increasingly use sketches, annotations, tools, and intermediate images during reasoning, but it remains unclear whether they truly rely on these visual states.
arXiv AI
3d ago
Reinforcing Multimodal Reasoning via Token-Level Perception-Grounded Advantage Estimation
arXiv:2609.39168v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has improved the reasoning capabilities of Multimodal Large Language Models (MLLMs), yet existing...
arXiv AI
Aug 6
Reasoning Dynamics and the Limits of Monitoring Modality Reliance in Vision-Language Models
arXiv:2604. 14888v3 Announce Type: replace-cross Abstract: Recent advances in vision language models (VLMs) offer reasoning capabilities, yet how these unfold and integrate visual and textual information remains unclear.
arXiv AI
Sep 7
When Seeing Overrides Knowing: Visual Dominance and Deferral-Based Method for Personalized Safety in VLMs
The paper introduces MPS-Bench, a benchmark of 5,181 scenarios from 584 real-world images across 12 high-risk domains, each paired with a hidden user profile, to evaluate personalized safety in vision‑language models (VLMs). Eight leading VLMs were tested and found to almost always respond directly (86‑99%) without seeking missing context, scoring no higher than 2.6/5 on personalized safety. The authors identify a phenomenon called visual dominance, where visual information enters text representations early and suppresses textual risk signals, and propose PRISM, a lightweight input monitor that predicts when a query should be deferred, achieving 0.978 AUC and outperforming all tested models on the safety‑utility Pareto frontier.
arXiv AI
Sep 1
Evidence-Grounded Trustworthy Multimodal Reasoning and Evaluation Benchmark in Complex Urban Scenes
arXiv:2506.09557v2 Announce Type: replace-cross Abstract: While Multimodal Large Language Models (MLLMs) demonstrate impressive performance in benign scenarios, their cognitive reliability deteriorat...
Hugging Face Trending Papers
Aug 24
Buried in Textual Debt: Context Pruning with Visual Evidence Preservation for MLLM Agents
Multimodal Large Language Models (MLLMs) are increasingly deployed as multi-step agents, where explicit reasoning supports task decomposition and tool coordination but also accumulates self-generated...
arXiv AI
Sep 25
Mind What Matters for Reasoning: Aligning Cross-Modal Attention via Selective Probability Mass Concentration
The paper introduces Selective Probability Mass Concentration (sPMC), a training framework that strengthens implicit visual grounding in multimodal large language models by selectively regularizing attention heads most responsive to visual evidence. sPMC treats attention over visual tokens as a spatial probability distribution and encourages mass to concentrate on semantically relevant regions using segmentation-derived priors, while leaving other heads unconstrained. Across six multimodal benchmarks, sPMC yields an average zero‑shot improvement of 3% and gains up to 11.3% for various models by regularizing only 3%–15% of their attention heads.