arXiv:2608. 00410v2 Announce Type: replace Abstract: Human language is highly polysemous.
arXiv:2609.12575v1 Announce Type: new Abstract: Ambiguity is often treated as a bug for AI systems to resolve---but in human communication and culture, ambiguity can also be a generative resource. Fr...
The paper investigates how multimodal large language models (MLLMs) handle conflicting evidence presented in text, image, or both forms. Across 13 MLLMs and two datasets, the authors find that models are not robust to knowledge conflict: they tend to accept contradictory image evidence more readily than contradictory text, and when both modalities conflict the preference is arbitrary, depending on input order, model, and dataset. The instability degrades multimodal retrieval-augmented generation and can be exploited by adversarial attacks, while simple mitigation techniques such as prompting, steering, and direct preference optimization largely fail, with supervised fine‑tuning offering only moderate improvement.
arXiv:2603. 04419v2 Announce Type: replace-cross Abstract: We characterize the phenomenon of context-dependent affordance computation in vision-language models (VLMs).
arXiv:2609.22206v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) have achieved remarkable performance across a wide range of multimodal tasks, yet understanding and quantify...
arXiv:2609.00293v1 Announce Type: new Abstract: We investigate how vision-language models (VLMs) handle context-memory conflicts; that is, situations in which the model is given information in contex...
arXiv:2609.07474v2 Announce Type: replace Abstract: Language models compute over tokens: language is their input, their output, and increasingly their internal representation. Whether language should...
arXiv:2606. 26348v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) can process diverse inputs, e.
arXiv:2605.02035v3 Announce Type: replace-cross Abstract: Ambiguity resolution is a key challenge in multimodal machine translation (MMT), where models must genuinely leverage visual input to map an...
The study investigates whether multimodal large language models (MLLMs) report bistable images, like the duck‑rabbit, in a manner similar to humans. Using the LLaVA family, researchers examined two dimensions: modulability (the influence of visual cues and linguistic priors) and exclusivity (whether responses commit to a single interpretation). Results show that both visual and linguistic manipulations shift reports in human‑consistent ways while maintaining predominantly exclusive responses, driven by competing image‑token representations and distinct bottom‑up and top‑down pathways.
arXiv:2605. 18160v2 Announce Type: replace-cross Abstract: In recent years, multimodal large language models (MLLMs) have achieved remarkable progress, primarily attributed to effective paradigms for integrating visual and textual information.
The paper investigates why multimodal large language models (MLLMs) struggle with vision‑centric tasks when visual evidence conflicts with pretrained language knowledge. Using image reconstruction and a new WhatIfVis benchmark, the authors show that MLLMs preserve coarse‑grained visual attributes but fail to consistently use them, and that supervised fine‑tuning and activation patching can improve controllability of visual context sensitivity. The study demonstrates that the main bottleneck lies in the models’ inability to reliably regulate their reliance on visual evidence rather than in visual perception itself.
arXiv:2606. 31407v1 Announce Type: cross Abstract: Vision-language models can produce confident answers on visually ambiguous inputs, resulting in biased predictions.