Related papers: DocShield: Towards AI Document Safety via Evidence…
Current AI-powered code assistance tools often struggle with poorly-defined problem statements that lack sufficient task context and requirements specification. Recent analysis of software engineering agents reveals that failures on such…
Causal thinking enables humans to understand not just what is seen, but why it happens. To replicate this capability in modern AI systems, we introduce the task of visual causal discovery. It requires models to infer cause-and-effect…
The emergence of generative pre-trained models has facilitated the synthesis of high-quality text, but it has also posed challenges in identifying factual errors in the generated text. In particular: (1) A wider range of tasks now face an…
Automated mental health prediction using textual data has shown promising results with deep learning and large language models. However, deploying these models in high-stakes real-world settings remains challenging, as existing approaches…
The advent of multimodal learning has brought a significant improvement in document AI. Documents are now treated as multimodal entities, incorporating both textual and visual information for downstream analysis. However, works in this…
In the age of powerful AI-generated text, automatic detectors have emerged to identify machine-written content. This poses a threat to author privacy and freedom, as text authored with AI assistance may be unfairly flagged. We propose…
Recent text-guided image editing (TIE) models have made remarkable progress, yet edited images still frequently suffer from fine-grained issues such as unnatural objects, lighting mismatch, and unexpected changes. Existing refinement…
The rapid proliferation of synthetic media, presentation attacks, and document forgeries has created significant vulnerabilities in Know Your Customer (KYC) workflows across financial services, telecommunications, and digital-identity…
With the advent of deep learning, text generation language models have improved dramatically, with text at a similar level as human-written text. This can lead to rampant misinformation because content can now be created cheaply and…
The development of generative artificial intelligence technologies has propelled the visual realism of synthetic images to an unprecedented level. Although current interpretable detection methods based on Large Multimodal Models (LMMs) have…
Recent advances in large language models (LLMs) have given rise to powerful coding agents, making it possible for code assistants to evolve into code engineers. However, existing methods still face significant challenges in achieving…
We present a novel evaluation paradigm for AI text detectors that prioritizes real-world and equitable assessment. Current approaches predominantly report conventional metrics like AUROC, overlooking that even modest false positive rates…
Designing document identifiers (docids) that carry rich semantic information while maintaining tractable search spaces is a important challenge in generative retrieval (GR). Popular codebook methods address this by building a hierarchical…
Recent agentic workflows automate professional document generation but focus narrowly on textual quality, overlooking structural and stylistic professionalism, which is equally critical for readability. This gap stems mainly from a lack of…
We have witnessed lately a rapid proliferation of advanced Large Language Models (LLMs) capable of generating high-quality text. While these LLMs have revolutionized text generation across various domains, they also pose significant risks…
The goal of document-grounded dialogue (DocGD) is to generate a response by grounding the evidence in a supporting document in accordance with the dialogue context. This process involves four variables that are causally connected. Recently,…
The proliferation of generative models, such as Generative Adversarial Networks (GANs), Diffusion Models, and Variational Autoencoders (VAEs), has enabled the synthesis of high-quality multimedia data. However, these advancements have also…
We present DocPuzzle, a rigorously constructed benchmark for evaluating long-context reasoning capabilities in large language models (LLMs). This benchmark comprises 100 expert-level QA problems requiring multi-step reasoning over long…
High-quality code documentation is crucial for software development especially in the era of AI. However, generating it automatically using Large Language Models (LLMs) remains challenging, as existing approaches often produce incomplete,…
The recent generative AI models' capability of creating realistic and human-like content is significantly transforming the ways in which people communicate, create and work. The machine-generated content is a double-edged sword. On one…