论文检索

Michal Golovanevsky, William Rudman, Michael A. Lepori, Amir Bar, Ritambhara Singh, Carsten Eickhoff

Multimodal Large Language Models (MLLMs) perform well on tasks such as visual question answering, but it remains unclear whether their reasoning relies more on memorized world knowledge or on the visual information present in the input image. To investigate this, we introduce Visual CounterFact, a new dataset of visually-realistic counterfactuals that put world knowledge priors (e.g, red strawberry) into direct conflict with visual input (e.g, blue strawberry). Using Visual CounterFact, we show that model predictions initially reflect memorized priors, but shift toward visual evidence in mid-to-late layers. This dynamic reveals a competition between the two modalities, with visual input ultimately overriding priors during evaluation. To control this behavior, we propose Pixels Versus Priors (PvP) steering vectors, a mechanism for controlling model outputs toward either world knowledge or visual input through activation-level interventions. On average, PvP successfully shifts 99.3% of color and 80.8% of size predictions from priors to counterfactuals. Together, these findings offer new tools for interpreting and controlling factual behavior in multimodal models.

Claudiu Daniel Hromei, Antonio Scaiella, Danilo Croce, Roberto Basili

Understanding natural language commands in situated Human-Robot Interaction (HRI) requires linking linguistic input to perceptual context. Traditional symbolic parsers lack the flexibility to operate in complex, dynamic environments. We introduce a novel Multimodal Grounded Semantic Role Labelling (G-SRL) framework that combines frame semantics with perceptual grounding, enabling robots to interpret commands via multimodal logical forms. Our approach leverages modern Visual Language Models (VLLMs), which jointly process text and images, and is supported by an automated pipeline that generates high-quality training data. Structured command annotations are converted into photorealistic scenes via LLM-guided prompt engineering and diffusion models, then rigorously validated through object detection and visual question answering. The pipeline produces over 11,000 image-command pairs (3,500+ manually validated), while approaching the quality of manually curated datasets at significantly lower cost.

Ruiran Su, Jiasheng Si, Zhijiang Guo, Janet B. Pierrehumbert

Scientific fact-checking has largely focused on textual and tabular sources, neglecting scientific charts—a primary medium for conveying quantitative evidence and supporting statistical reasoning in research communication. We introduce ClimateViz, the first large-scale benchmark for scientific fact-checking grounded in real-world, expert-curated scientific charts. ClimateViz comprises 49,862 claims paired with 2,896 visualizations, each labeled as support, refute, or not enough information. To enable interpretable verification, each instance includes structured knowledge graph explanations that capture statistical patterns, temporal trends, spatial comparisons, and causal relations. We conduct a comprehensive evaluation of state-of-the-art multimodal large language models, including proprietary and open-source ones, under zero-shot and few-shot settings. Our results show that current models struggle to perform fact-checking when statistical reasoning over charts is required: even the best-performing systems, such as Gemini 2.5 and InternVL 2.5, achieve only 76.2–77.8% accuracy in label-only output settings, which is far below human performance (89.3% and 92.7%). While few-shot prompting yields limited improvements, explanation-augmented outputs significantly enhance performance in some closed-source models, notably o3 and Gemini 2.5.

Manan Suri, Puneet Mathur, Nedim Lipka, Franck Dernoncourt, Ryan A. Rossi, Vivek Gupta, Dinesh Manocha

Flowcharts are a critical tool for visualizing decision-making processes. However, their non-linear structure and complex visual-textual relationships make it challenging to interpret them using LLMs, as vision-language models frequently hallucinate nonexistent connections and decision paths when analyzing these diagrams. This leads to compromised reliability for automated flowchart processing in critical domains such as logistics, health, and engineering. We introduce the task of Fine-grained Flowchart Attribution, which traces specific components grounding a flowchart referring LLM response. Flowchart Attribution ensures the verifiability of LLM predictions and improves explainability by linking generated responses to the flowchart’s structure. We propose FlowPathAgent, a neurosymbolic agent that performs fine-grained post hoc attribution through graph-based reasoning. It first segments the flowchart, then converts it into a structured symbolic graph, and then employs an agentic approach to dynamically interact with the graph, to generate attribution paths. Additionally, we present FlowExplainBench, a novel benchmark for evaluating flowchart attributions across diverse styles, domains, and question types. Experimental results show that FlowPathAgent mitigates visual hallucinations in LLM answers over flowchart QA, outperforming strong baselines by 10–14% on our proposed FlowExplainBench dataset.

Heekyung Lee, Jiaxin Ge, Tsung-Han Wu, Minwoo Kang, Trevor Darrell, David M. Chan

Rebus puzzles, visual riddles that encode language through imagery, spatial arrangement, and symbolic substitution, pose a unique challenge to current vision-language models (VLMs). Unlike traditional image captioning or question answering tasks, rebus solving requires multimodal abstraction, symbolic reasoning, and a grasp of cultural, phonetic and linguistic puns. In this short paper, we investigate the capacity of contemporary VLMs to interpret and solve rebus puzzles by constructing a hand-generated and annotated benchmark of diverse english-language rebus puzzles, ranging from simple pictographic substitutions to spatially-dependent cues (“head” over “heels”). We analyze how different VLMs perform, and our findings reveal that while VLMs exhibit some surprising capabilities in decoding simple visual clues, they struggle significantly with tasks requiring abstract reasoning, lateral thinking, and understanding visual metaphors.

Sohee Kim, Soohyun Ryu, Joonhyung Park, Eunho Yang

Large Vision-Language Models (LVLMs) generate contextually relevant responses by jointly interpreting visual and textual inputs. However, our finding reveals they often mistakenly perceive text inputs lacking visual evidence as being part of the image, leading to erroneous responses. In light of this finding, we probe whether LVLMs possess an internal capability to determine if textual concepts are grounded in the image, and discover a specific subset of Feed-Forward Network (FFN) neurons, termed Visual Absence-aware (VA) neurons, that consistently signal the visual absence through a distinctive activation pattern. Leveraging these patterns, we develop a detection module that systematically classifies whether an input token is visually grounded. Guided by its prediction, we propose a method to refine the outputs by reinterpreting question prompts or replacing the detected absent tokens during generation. Extensive experiments show that our method effectively mitigates the models’ tendency to falsely presume the visual presence of text input and its generality across various LVLMs.

Xinpan Yuan, Mingzhu Huang, Liujie Hua, Jianuo Ju, Xu Zhang

Accurate grading of rhinitis severity in nasal endoscopy relies heavily on the characterization of key secretion types, notably clear nasal discharge (CND) and purulent nasal secretion (PUS). However, both exhibit ambiguous appearance and high structural variability, posing challenges to automated grading under weak supervision. To address this, we propose Multimodal Learning for Mucus Anomaly Grading (MMAG), which integrates structured prompts with rank-aware vision-language modeling for joint detection and grading. Attribute prompts are constructed from clinical descriptors (e.g., secretion type, severity, location) and aligned with multi-level visual features via a dual-branch encoder. During inference, the model localizes mucus anomalies and maps the input image to severity-specific prompts (e.g., “moderate pus”), projecting them into a rank-aware feature space for progressive similarity scoring.Extensive evaluations on CND and PUS datasets show that our method achieves consistent gains over Baseline, improving AUC by 6.31% and 4.79%, and F1 score by 12.85% and 6.03%, respectively.This framework enables interpretable, annotation-efficient, and semantically grounded assessment of rhinitis severity based on mucus anomalies.

Sofia Jamil, Kotla Sai Charan, Sriparna Saha, Koustava Goswami, Joseph K J

Poetry is an expressive form of art that invites multiple interpretations, as readers often bring their own emotions, experiences, and cultural backgrounds into their understanding of a poem. Recognizing this, we aim to generate images for poems and improve these images in a zero-shot setting, enabling audiences to modify images as per their requirements. To achieve this, we introduce a novel \textit{Weighted Prompt Manipulation (WPM)} technique, which systematically modifies attention weights and text embeddings within diffusion models. By dynamically adjusting the importance of specific words, \textit{WPM} enhances or suppresses their influence in the final generated image, leading to semantically richer and more contextually accurate visualizations. Our approach exploits diffusion models and large language models (LLMs) such as GPT in conjunction with existing poetry datasets, ensuring a comprehensive and structured methodology for improved image generation in the literary domain. To the best of our knowledge, this is the first attempt at integrating weighted prompt manipulation for enhancing imagery in poetic language.

Jian Zhang, Junyi Guo, Junyi Yuan, Huanda Lu, Yanlin Zhou, Fangyu Wu, Qiufeng Wang, Dongming Lu

Cross-modal retrieval is essential for interpreting cultural heritage data, but its effectiveness is often limited by incomplete or inconsistent textual descriptions, caused by historical data loss and the high cost of expert annotation. While large language models (LLMs) offer a promising solution by enriching textual descriptions, their outputs frequently suffer from hallucinations or miss visually grounded details. To address these challenges, we propose C^3, a data augmentation framework that enhances cross-modal retrieval performance by improving the completeness and consistency of LLM-generated descriptions. C^3 introduces a bidirectional validation mechanism to assess semantic coverage using both visual cues and language-model outputs. Furthermore, to mitigate factual inconsistencies, we formulate a Markov Decision Process to supervise Chain-of-Thought reasoning, guiding consistency verification through adaptive query control. Experiments on the cultural heritage dataset CulTi and general benchmarks MSCOCO and Flickr30K demonstrate that C^3 achieves state-of-the-art performance in both fine-tuned and zero-shot settings.

Qidong Wang, Junjie Hu, Ming Jiang

Recent advances in causal interpretability have extended from language models to vision-language models (VLMs), seeking to reveal their internal mechanisms through input interventions. While textual interventions often target semantics, visual interventions typically rely on coarse pixel-level perturbations, limiting semantic insights on multimodal integration. In this study, we introduce V-SEAM, a novel framework that combines **V**isual **S**emantic **E**diting and **A**ttention **M**odulating for causal interpretation of VLMs. V-SEAM enables concept-level visual manipulations and identifies attention heads with positive or negative contributions to predictions across three semantic levels: objects, attributes, and relationships. We observe that positive heads are often shared within the same semantic level but vary across levels, while negative heads tend to generalize broadly. Finally, we introduce an automatic method to modulate key head embeddings, demonstrating enhanced performance for both LLAVA and InstructBLIP across three diverse VQA benchmarks. Our data and code are released at: https://github.com/petergit1/V-SEAM.

Gagan Mundada, Yash Vishe, Amit Namburi, Xin Xu, Zachary Novack, Julian McAuley, Junda Wu

Recent advances in Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities across various vision-language tasks. However, their reasoning abilities in the multimodal symbolic music domain remain largely unexplored.We introduce WildScore, the first in-the-wild multimodal symbolic music reasoning and analysis benchmark, designed to evaluate MLLMs’ capacity to interpret real-world music scores and answer complex musicological queries. Each instance in WildScore is sourced from genuine musical compositions and accompanied by authentic user-generated questions and discussions, capturing the intricacies of practical music analysis. To facilitate a comprehensive evaluation, we propose a systematic taxonomy,comprising both high-level and fine-grained musicological ontologies. Furthermore, we frame complex music reasoning as multiple-choice question answering,enabling controlled and scalable assessment of MLLMs’ symbolic music understanding. Empirical benchmarking of state-of-the-art MLLMs on WildScore reveals intriguing patterns in their visual-symbolic reasoning, uncovering both promising directions and persistent challenges for MLLMs in symbolic music reasoning and analysis.We release the dataset and code.

Runjia Zeng, Guangyan Sun, Qifan Wang, Tong Geng, Sohail Dianat, Xiaotian Han, Raghuveer Rao, Xueling Zhang, Cheng Han, Lifu Huang 等

Considering deep neural networks as manifold mappers, the pretrain-then-fine-tune paradigm can be interpreted as a two-stage process: pretrain establishes a broad knowledge base, and fine-tune adjusts the model parameters to activate specific neural pathways to align with the target manifold. Although prior fine-tuning approaches demonstrate success, their rigid parameter space limits their ability to dynamically activate appropriate neural pathways, rendering them ill-equipped to adapt flexibly to the diverse and evolving data distributions. In light of this view, we propose a novel approach, Mixture of Expert Prompt Tuning (MEPT), as an effective and efficient manifold-mapping framework. MEPT leverages the Mixture of Experts architecture by integrating multiple prompt experts to adaptively learn diverse and non-stationary data distributions. Empirical evaluations demonstrate that MEPT outperforms several state-of-the-art parameter efficient baselines on SuperGLUE, achieving notable improvements in mean accuracy (e.g., 1.94%) while significantly reducing activated prompts by 79.25%. The effectiveness of MEPT is further supported by theoretical insights from manifold learning and validated through neural activation pathway visualization results. Our code is avaliable at https://runjia.tech/emnlp_mept/.

Xiaolong Wang, Zhaolu Kang, Wangyuxuan Zhai, Xinyue Lou, Yunghwei Lai, Ziyue Wang, Yawen Wang, Kaiyu Huang, Yile Wang, Peng Li 等

Multimodal Large Language Models (MLLMs) have demonstrated significant advances across numerous vision-language tasks. Due to their strong performance in image-text alignment, MLLMs can effectively understand image-text pairs with clear meanings. However, effectively resolving the inherent ambiguities in natural language and visual contexts remains challenging. Existing multimodal benchmarks typically overlook linguistic and visual ambiguities, relying mainly on unimodal context for disambiguation and thus failing to exploit the mutual clarification potential between modalities. To bridge this gap, we introduce MUCAR, a novel and challenging benchmark designed explicitly for evaluating multimodal ambiguity resolution across multilingual and cross-modal scenarios. MUCAR includes: (1) a multilingual dataset where ambiguous textual expressions are uniquely resolved by corresponding visual contexts, and (2) a dual-ambiguity dataset that systematically pairs ambiguous images with ambiguous textual contexts, with each combination carefully constructed to yield a single, clear interpretation through mutual disambiguation. Extensive evaluations involving 19 state-of-the-art multimodal models—encompassing both open-source and proprietary architectures—reveal substantial gaps compared to human-level performance, highlighting the need for future research into more sophisticated cross-modal ambiguity comprehension methods, further pushing the boundaries of multimodal reasoning.

Yiwen Jiang, Deval Mehta, Siyuan Yan, Yaling Shen, Zimu Wang, Zongyuan Ge

Multimodal Large Language Models (MLLMs) have shown promise in visual-textual reasoning, with Multimodal Chain-of-Thought (MCoT) prompting significantly enhancing interpretability. However, existing MCoT methods rely on rationale-rich datasets and largely focus on inter-object reasoning, overlooking the intra-object understanding crucial for image classification. To address this gap, we propose WISE, a Weak-supervision-guided Step-by-step Explanation method that augments any image classification dataset with MCoTs by reformulating the concept-based representations from Concept Bottleneck Models (CBMs) into concise, interpretable reasoning chains under weak supervision. Experiments across ten datasets show that our generated MCoTs not only improve interpretability by 37% but also lead to gains in classification accuracy when used to fine-tune MLLMs. Our work bridges concept-based interpretability and generative MCoT reasoning, providing a generalizable framework for enhancing MLLMs in fine-grained visual understanding.

Sangyeon Cho, Mingi Kim, Jinkwon Hwang, Jaehoon Go, Minuk Ma, Sunjae Yoon, Junyeong Kim

Automated Audio Captioning (AAC) aims to generate natural language descriptions of audio content, enabling machines to interpret and communicate complex acoustic scenes. However, current AAC datasets often suffer from short and simplistic captions, limiting model expressiveness and semantic depth. To address this, we introduce **VggCaps**, a new multi-modal dataset that pairs audio with corresponding video and leverages large language models (LLMs) to generate rich, descriptive captions. VggCaps significantly outperforms existing benchmarks in caption length, lexical diversity, and human-rated quality. Furthermore, we propose **Multi2Cap**, a novel AAC framework that learns audio-visual representations through a AV-grounding module during pre-training and reconstructs visual semantics using audio alone at inference. This enables visually grounded captioning in audio-only scenarios. Experimental results on Clotho and AudioCaps demonstrate that Multi2Cap achieves state-of-the-art performance across multiple metrics, validating the effectiveness of cross-modal supervision and LLM-based generation in advancing AAC.

Zixin Chen, Sicheng Song, KaShun Shum, Yanna Lin, Rui Sheng, Weiqi Wang, Huamin Qu

Misleading visualizations, which manipulate chart representations to support specific claims, can distort perception and lead to incorrect conclusions. Despite decades of research, they remain a widespread issue, posing risks to public understanding and raising safety concerns for AI systems involved in data-driven communication. While recent multimodal large language models (MLLMs) show strong chart comprehension abilities, their capacity to detect and interpret misleading charts remains unexplored. We introduce Misleading ChartQA benchmark, a large-scale multimodal dataset designed to evaluate MLLMs on misleading chart reasoning. It contains 3,026 curated examples spanning 21 misleader types and 10 chart types, each with standardized chart code, CSV data, multiple-choice questions, and labeled explanations, validated through iterative MLLM checks and exhausted expert human review. We benchmark 24 state-of-the-art MLLMs, analyze their performance across misleader types and chart formats, and propose a novel region-aware reasoning pipeline that enhances model accuracy. Our work lays the foundation for developing MLLMs that are robust, trustworthy, and aligned with the demands of responsible visual communication.

Zhuoyuan Mao, Mengjie Zhao, Qiyu Wu, Hiromi Wakaki, Yuki Mitsufuji

Recent advancements in music large language models (LLMs) have significantly improved music understanding tasks, which involve the model’s ability to analyze and interpret various musical elements. These improvements primarily focused on integrating both music and text inputs. However, the potential of incorporating additional modalities such as images, videos and textual music features to enhance music understanding remains unexplored. To bridge this gap, we propose DeepResonance, a multimodal music understanding LLM fine-tuned via multi-way instruction tuning with multi-way aligned music, text, image, and video data. To this end, we construct Music4way-MI2T, Music4way-MV2T, and Music4way-Any2T, three 4-way training and evaluation datasets designed to enable DeepResonance to integrate both visual and textual music feature content. We also introduce multi-sampled ImageBind embeddings and a pre-LLM fusion Transformer to enhance modality fusion prior to input into text LLMs, tailoring for multi-way instruction tuning. Our model achieves state-of-the-art performances across six music understanding tasks, highlighting the benefits of the auxiliary modalities and the structural superiority of DeepResonance. We open-source the codes, models and datasets we constructed: https://github.com/sony/DeepResonance.

Ali Salamatian, Amirhossein Abaskohi, Wan-Cyuan Fan, Mir Rayat Imtiaz Hossain, Leonid Sigal, Giuseppe Carenini

Charts are a crucial visual medium for communicating and representing information. While Large Vision-Language Models (LVLMs) have made progress on chart question answering (CQA), the task remains challenging, particularly when models attend to irrelevant regions of the chart. In this work, we present ChartGaze, a new eye-tracking dataset that captures human gaze patterns during chart reasoning tasks. Through a systematic comparison of human and model attention, we find that LVLMs often diverge from human gaze, leading to reduced interpretability and accuracy. To address this, we propose a gaze-guided attention refinement that aligns image-text attention with human fixations. Our approach improves both answer accuracy and attention alignment, yielding gains of up to 2.56 percentage points across multiple models. These results demonstrate the promise of incorporating human gaze to enhance both the reasoning quality and interpretability of chart-focused LVLMs.

Amirhossein Abaskohi, Raymond Li, Chuyuan Li, Shafiq Joty, Giuseppe Carenini

We introduce CEMTM, a context-enhanced multimodal topic model designed to infer coherent and interpretable topic structures from both short and long documents containing text and images. CEMTM builds on fine-tuned large vision language models (LVLMs) to obtain contextualized embeddings, and employs a distributional attention mechanism to weight token-level contributions to topic inference. A reconstruction objective aligns topic-based representations with the document embedding, encouraging semantic consistency across modalities. Unlike existing approaches, CEMTM can process multiple images per document without repeated encoding and maintains interpretability through explicit word-topic and document-topic distributions. Extensive experiments on six multimodal benchmarks show that CEMTM consistently outperforms unimodal and multimodal baselines, achieving a remarkable average LLM score of 2.61. Further analysis shows its effectiveness in downstream few-shot retrieval and its ability to capture visually grounded semantics in complex domains such as scientific articles.

Yilun Liu, Minggui He, Feiyu Yao, Yuhe Ji, Shimin Tao, Jingzhou Du, Justin Li, Jian Gao, Zhang Li, Hao Yang 等

The emergence of text-to-image synthesis (TIS) models has significantly influenced digital image creation by producing high-quality visuals from written descriptions. Yet these models are sensitive on textual prompts, posing a challenge for novice users who may not be familiar with TIS prompt writing. Existing solutions relieve this via automatic prompt expansion or generation from a user query. However, this single-turn manner suffers from limited user-centricity in terms of result interpretability and user interactivity. Thus, we propose DialPrompt, a dialogue-based TIS prompt generation model that emphasizes user experience for novice users. DialPrompt is designed to follow a multi-turn workflow, where in each round of dialogue the model guides user to express their preferences on possible optimization dimensions before generating the final TIS prompt. To achieve this, we mined 15 essential dimensions for high-quality prompts from advanced users and curated a multi-turn dataset. Through training on this dataset, DialPrompt improves user-centricity by allowing users to perceive and control the creation process of TIS prompts. Experiments indicate that DialPrompt improves significantly in user-centricity score compared with existing approaches while maintaining a competitive quality of synthesized images. In our user evaluation, DialPrompt is highly rated by 19 human reviewers (especially novices).