Spandana Gella

Sai Rajeswar

Understanding diverse web data and automating web development presents an exciting challenge for agentic AI. While existing benchmarks addre… (voir plus)ss isolated web-based tasks—such as website-based Visual Question Answering (VQA) and UI-to-code generation—they lack a unified evaluation suite for assessing web agents that interact with and reason about web environments. We introduce WebMMU, a large-scale benchmark for evaluating AI-driven web agents across multilingual website VQA, HTML/CSS/JavaScript code editing, and sketch-to-code generation. WebMMU provides a comprehensive evaluation suite with real-world website data, multi-step reasoning tasks, and functional UI understanding. Benchmarking state-of-the-art multimodal models on WebMMU reveals significant limitations in web-based reasoning, layout understanding, and structured code generation, particularly in preserving UI hierarchy, handling multilingual content, and producing robust, functional code. While most existing models are optimized for English-only settings, WebMMU highlights the challenges of cross-lingual adaptation in real-world web development. These findings expose critical gaps in current models’ ability to understand website structures, execute user instructions, and generate high-quality web code, underscoring the need for more advanced multimodal reasoning in AI-driven web understanding and development.

2025-03-05

ICLR.cc/2025/Workshop/DL4C (publié)

WebMMU: A Benchmark for Multimodal Multilingual Website Understanding and Code Generation

Mahsa Massoud

David Vazquez

Juan A. Rodriguez

Perouz Taslakian

Sai Rajeswar

ServiceNow

WebMMU Benchmark

Understanding diverse web data and automating web development presents an exciting challenge for agentic AI. While existing benchmarks addre… (voir plus)ss isolated web-based tasks—such as website-based Visual Question Answering (VQA) and UI-to-code generation—they lack a unified evaluation suite for assessing web agents that interact with and reason about web environments. We introduce WebMMU, a large-scale benchmark for evaluating AI-driven web agents across multilingual website VQA, HTML/CSS/JavaScript code editing, and sketch-to-code generation. WebMMU provides a comprehensive evaluation suite with real-world website data, multi-step reasoning tasks, and functional UI understanding. Benchmarking state-of-the-art multimodal models on WebMMU reveals significant limitations in web-based reasoning, layout understanding, and structured code generation, particularly in preserving UI hierarchy, handling multilingual content, and producing robust, functional code. While most existing models are optimized for English-only settings, WebMMU highlights the challenges of cross-lingual adaptation in real-world web development. These findings expose critical gaps in current models’ ability to understand website structures, execute user instructions, and generate high-quality web code, underscoring the need for more advanced multimodal reasoning in AI-driven web understanding and development.

2025-03-05

ICLR.cc/2025/Workshop/DL4C (publié)

PairBench: Are Vision-Language Models Reliable at Comparing What They See?

Sai Rajeswar

Adriana Romero Soriano

Reihaneh Rabbany

Valentina Zantedeschi

Joao Monteiro

Understanding how effectively large vision language models (VLMs) compare visual inputs is crucial across numerous applications, yet this fu… (voir plus)ndamental capability remains insufficiently assessed. While VLMs are increasingly deployed for tasks requiring comparative judgment, including automated evaluation, re-ranking, and retrieval-augmented generation, no systematic framework exists to measure their performance in these scenarios. We present PairBench, a simple framework that evaluates VLMs as customizable similarity tools using widely available image datasets. Our approach introduces four key metrics for reliable comparison: alignment with human annotations, consistency across pair ordering, distribution smoothness, and controllability through prompting. Our analysis reveals that no model consistently excels across all metrics, with each demonstrating distinct strengths and weaknesses. Most concerning is the widespread inability of VLMs to maintain symmetric similarity scores. Interestingly, we demonstrate that performance on our benchmark strongly correlates with popular benchmarks used for more complex tasks, while providing additional metrics into controllability, smoothness and ordering. This makes PairBench a unique and comprehensive framework to evaluate the performance of VLMs for automatic evaluation depending on the task.

2025-02-21

ArXiv (prépublication)

PairBench: A Systematic Framework for Selecting Reliable Judge VLMs

Sai Rajeswar

Adriana Romero Soriano

Reihaneh Rabbany

Valentina Zantedeschi

Joao Monteiro

As large vision language models (VLMs) are increasingly used as automated evaluators, understanding their ability to effectively compare dat… (voir plus)a pairs as instructed in the prompt becomes essential. To address this, we present PairBench, a low-cost framework that systematically evaluates VLMs as customizable similarity tools across various modalities and scenarios. Through PairBench, we introduce four metrics that represent key desiderata of similarity scores: alignment with human annotations, consistency for data pairs irrespective of their order, smoothness of similarity distributions, and controllability through prompting. Our analysis demonstrates that no model, whether closed- or open-source, is superior on all metrics; the optimal choice depends on an auto evaluator's desired behavior (e.g., a smooth vs. a sharp judge), highlighting risks of widespread adoption of VLMs as evaluators without thorough assessment. For instance, the majority of VLMs struggle with maintaining symmetric similarity scores regardless of order. Additionally, our results show that the performance of VLMs on the metrics in PairBench closely correlates with popular benchmarks, showcasing its predictive power in ranking models.

2025-02-21

ArXiv (prépublication)

BigDocs: An Open Dataset for Training Multimodal Models on Document and Code Tasks

Juan A. Rodriguez

Xiangru Jian

Siba Smarak Panigrahi

Tianyu Zhang

Abhay Puri

Akshay Kalkunte Suresh

François Savard

Ahmed Masry

Shravan Nayak

Rabiul Awal

Mahsa Massoud

Amirhossein Abaskohi

Zichao Li

Suyuchen Wang

Pierre-Andre Noel

Mats Leon Richter

Saverio Vadacchino

Shubham Agarwal

Sanket Biswas … (voir 19 de plus)

Sara Shanian

Ying Zhang

Sathwik Tejaswi Madhusudhan

Joao Monteiro

Krishnamurthy Dj Dvijotham

Torsten Scholak

Nicolas Chapados

Sepideh Kharaghani

Sean Hughes

M. Özsu

Issam Hadj Laradji

Perouz Taslakian

David Vazquez

Sai Rajeswar

Multimodal AI has the potential to significantly enhance document-understanding tasks, such as processing receipts, understanding workflows,… (voir plus) extracting data from documents, and summarizing reports. Code generation tasks that require long-structured outputs can also be enhanced by multimodality. Despite this, their use in commercial applications is often limited due to limited access to relevant training data and restrictive licensing, which hinders open access. To address these limitations, we introduce BigDocs-7.5M, a high-quality, open-access dataset comprising 7.5 million multimodal documents across 30 tasks. We use an efficient data curation process to ensure that our data is high quality and license-permissive. Our process emphasizes accountability, responsibility, and transparency through filtering rules, traceable metadata, and careful content analysis. Additionally, we introduce BigDocs-Bench,, a benchmark suite with 10 novel tasks where we carefully create datasets that reflect real-world use cases involving reasoning over Graphical User Interfaces (GUI) and code generation from images. Our experiments show that training with BigDocs-Bench, improves average performance up to 25.8% over closed-source GPT-4o in document reasoning and structured output tasks such as Screenshot2HTML or Image2Latex generation. Finally, human evaluations revealed that participants preferred the outputs from models trained with BigDocs over those from GPT-4o. This suggests that BigDocs can help both academics and the open-source community utilize and improve AI tools to enhance multimodal capabilities and document reasoning.

2025-01-22

ICLR.cc/2025/Conference (poster)

BigDocs: An Open Dataset for Training Multimodal Models on Document and Code Tasks

Juan A. Rodriguez

Xiangru Jian

Siba Smarak Panigrahi

Tianyu Zhang

Abhay Puri

Akshay Kalkunte Suresh

François Savard

Ahmed Masry

Shravan Nayak

Rabiul Awal

Mahsa Massoud

Amirhossein Abaskohi

Zichao Li

Suyuchen Wang

Pierre-Andre Noel

Mats Leon Richter

Saverio Vadacchino

Shubham Agarwal

Sanket Biswas … (voir 23 de plus)

Sara Shanian

Ying Zhang

Noah Bolger

Kurt MacDonald

Simon Fauvel

Sathwik Tejaswi Madhusudhan

Srinivas Sunkara

Joao Monteiro

Krishnamurthy Dj Dvijotham

Torsten Scholak

Nicolas Chapados

Sepideh Kharaghani

Sean Hughes

M. Özsu

Issam Hadj Laradji

Perouz Taslakian

David Vazquez

Sai Rajeswar

2025-01-22

ICLR.cc/2025/Conference (poster)

PairBench: A Systematic Framework for Selecting Reliable Judge VLMs

Sai Rajeswar

Adriana Romero Soriano

Reihaneh Rabbany

Valentina Zantedeschi

Joao Monteiro

As large vision language models (VLMs) are increasingly used as automated evaluators, understanding their ability to effectively compare dat… (voir plus)a pairs as instructed in the prompt becomes essential. To address this, we present PairBench, a low-cost framework that systematically evaluates VLMs as customizable similarity tools across various modalities and scenarios. Through PairBench, we introduce four metrics that represent key desiderata of similarity scores: alignment with human annotations, consistency for data pairs irrespective of their order, smoothness of similarity distributions, and controllability through prompting. Our analysis demonstrates that no model, whether closed- or open-source, is superior on all metrics; the optimal choice depends on an auto evaluator's desired behavior (e.g., a smooth vs. a sharp judge), highlighting risks of widespread adoption of VLMs as evaluators without thorough assessment. For instance, the majority of VLMs struggle with maintaining symmetric similarity scores regardless of order. Additionally, our results show that the performance of VLMs on the metrics in PairBench closely correlates with popular benchmarks, showcasing its predictive power in ranking models.

2025-01-01

arXiv.org (prépublication)

BigDocs: An Open and Permissively-Licensed Dataset for Training Multimodal Models on Document and Code Tasks

Juan A. Rodriguez

Xiangru Jian

Siba Smarak Panigrahi

Tianyu Zhang

Abhay Puri

Akshay Kalkunte Suresh

François Savard

Ahmed Masry

Shravan Nayak

Rabiul Awal

Mahsa Massoud

Amirhossein Abaskohi

Zichao Li

Suyuchen Wang

Pierre-Andre Noel

Mats Leon Richter

Saverio Vadacchino

Shubham Agarwal

Sanket Biswas … (voir 23 de plus)

Sara Shanian

Ying Zhang

Noah Bolger

Kurt MacDonald

Simon Fauvel

Sathwik Tejaswi Madhusudhan

Srinivas Sunkara

Joao Monteiro

Krishnamurthy Dj Dvijotham

Torsten Scholak

Nicolas Chapados

Sepideh Kharaghani

Sean Hughes

M. Özsu

Issam Hadj Laradji

Perouz Taslakian

David Vazquez

Sai Rajeswar

Multimodal AI has the potential to significantly enhance document-understanding tasks, such as processing receipts, understanding workflows,… (voir plus) extracting data from documents, and summarizing reports. Code generation tasks that require long-structured outputs can also be enhanced by multimodality. Despite this, their use in commercial applications is often limited due to limited access to training data and restrictive licensing, which hinders open access. To address these limitations, we introduce BigDocs-7.5M, a high-quality, open-access dataset comprising 7.5 million multimodal documents across 30 tasks. We use an efficient data curation process to ensure our data is high-quality and license-permissive. Our process emphasizes accountability, responsibility, and transparency through filtering rules, traceable metadata, and careful content analysis. Additionally, we introduce BigDocs-Bench, a benchmark suite with 10 novel tasks where we create datasets that reflect real-world use cases involving reasoning over Graphical User Interfaces (GUI) and code generation from images. Our experiments show that training with BigDocs-Bench improves average performance up to 25.8% over closed-source GPT-4o in document reasoning and structured output tasks such as Screenshot2HTML or Image2Latex generation. Finally, human evaluations showed a preference for outputs from models trained on BigDocs over GPT-4o. This suggests that BigDocs can help both academics and the open-source community utilize and improve AI tools to enhance multimodal capabilities and document reasoning. The project is hosted at https://bigdocs.github.io .

2024-10-10

NeurIPS.cc/2024/Workshop/RBFM (poster)

Using In-Context Learning to Improve Dialogue Safety

Nicholas Meade

Devamanyu Hazarika

Prakhar Gupta

Di Jin

Siva Reddy

Yang Liu

Dilek Hakkani-Tur

2023-10-07

EMNLP/2023/Conference (publié)

Words Aren’t Enough, Their Order Matters: On the Robustness of Grounding Visual Referring Expressions

Arjun Reddy Akula

Yaser Al-Onaizan

Song-Chun Zhu

Siva Reddy

Visual referring expression recognition is a challenging task that requires natural language understanding in the context of an image. We cr… (voir plus)itically examine RefCOCOg, a standard benchmark for this task, using a human study and show that 83.7% of test instances do not require reasoning on linguistic structure, i.e., words are enough to identify the target object, the word order doesn’t matter. To measure the true progress of existing models, we split the test set into two sets, one which requires reasoning on linguistic structure and the other which doesn’t. Additionally, we create an out-of-distribution dataset Ref-Adv by asking crowdworkers to perturb in-domain examples such that the target object changes. Using these datasets, we empirically show that existing methods fail to exploit linguistic structure and are 12% to 23% lower in performance than the established progress for this task. We also propose two methods, one based on contrastive learning and the other based on multi-task learning, to increase the robustness of ViLBERT, the current state-of-the-art model for this task. Our datasets are publicly available at https://github.com/aws/aws-refcocog-adv.

2020-07-01

Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (publié)