The proliferation of generative AI has led to hyper-realistic synthetic videos, escalating misuse risks and outstripping binary real/fake detectors. We introduce SAGA (Source Attribution of Generative AI videos), the first comprehensive framework to address the urgent need for AI-generated video source attribution at a large scale. Unlike traditional detection, SAGA identifies the specific generative model used. It uniquely provides multi-granular attribution across five levels: authenticity, generation task (e.g., T2V/I2V), model version, development team, and the precise generator, offering far richer forensic insights. Our novel video transformer architecture, leveraging features from a robust vision foundation model, effectively captures spatio-temporal artifacts. Critically, we introduce a data-efficient pretrain-and-attribute strategy, enabling SAGA to achieve state-of-the-art attribution using only 0.5\% of source-labeled data per class, matching fully supervised performance. Furthermore, we propose Temporal Attention Signatures (T-Sigs), a novel interpretability method that visualizes learned temporal differences, offering the first explanation for why different video generators are distinguishable. Extensive experiments on public datasets, including cross-domain scenarios, demonstrate that SAGA sets a new benchmark for synthetic video provenance, providing crucial, interpretable insights for forensic and regulatory applications.

Large Language Models (LLMs) in search applications increasingly prioritize verbose, lexically complex responses that paradoxically reduce user satisfaction and engagement. Through a comprehensive study of 10.000 (est.) participants comparing responses from five major AI-powered search systems, we demonstrate that users overwhelmingly prefer concise, source-attributed responses over elaborate explanations. Our analysis reveals that current AI development trends toward "artificial sophistication" create an uncanny valley effect where systems sound knowledgeable but lack genuine critical thinking, leading to reduced trust and increased cognitive load. We present evidence that optimal AI communication mirrors effective human discourse: direct, properly sourced, and honest about limitations. Our findings challenge the prevailing assumption that more complex AI responses indicate better performance, instead suggesting that human-like brevity and transparency are key to user engagement and system reliability.

While attribution methods, such as Shapley values, are widely used to explain the importance of features or training data in traditional machine learning, their application to Large Language Models (LLMs), particularly within Retrieval-Augmented Generation (RAG) systems, is nascent and challenging. The primary obstacle is the substantial computational cost, where each utility function evaluation involves an expensive LLM call, resulting in direct monetary and time expenses. This paper investigates the feasibility and effectiveness of adapting Shapley-based attribution to identify influential retrieved documents in RAG. We compare Shapley with more computationally tractable approximations and some existing attribution methods for LLM. Our work aims to: (1) systematically apply established attribution principles to the RAG document-level setting; (2) quantify how well SHAP approximations can mirror exact attributions while minimizing costly LLM interactions; and (3) evaluate their practical explainability in identifying critical documents, especially under complex inter-document relationships such as redundancy, complementarity, and synergy. This study seeks to bridge the gap between powerful attribution techniques and the practical constraints of LLM-based RAG systems, offering insights into achieving reliable and affordable RAG explainability.

The rapid evolution of large language models (LLMs) represents a substantial leap forward in natural language understanding and generation. However, alongside these advancements come significant challenges related to the accountability and transparency of LLM responses. Reliable source attribution is essential to adhering to stringent legal and regulatory standards, including those set forth by the General Data Protection Regulation. Despite the well-established methods in source attribution within the computer vision domain, the application of robust attribution frameworks to natural language processing remains underexplored. To bridge this gap, we propose a novel and versatile TRansformer-based Attribution framework using Contrastive Embeddings called TRACE that, in particular, exploits contrastive learning for source attribution. We perform an extensive empirical evaluation to demonstrate the performance and efficiency of TRACE in various settings and show that TRACE significantly improves the ability to attribute sources accurately, making it a valuable tool for enhancing the reliability and trustworthiness of LLMs.

While humans increasingly rely on large language models (LLMs), they are susceptible to generating inaccurate or false information, also known as "hallucinations". Technical advancements have been made in algorithms that detect hallucinated content by assessing the factuality of the model's responses and attributing sections of those responses to specific source documents. However, there is limited research on how to effectively communicate this information to users in ways that will help them appropriately calibrate their trust toward LLMs. To address this issue, we conducted a scenario-based study (N=104) to systematically compare the impact of various design strategies for communicating factuality and source attribution on participants' ratings of trust, preferences, and ease in validating response accuracy. Our findings reveal that participants preferred a design in which phrases within a response were color-coded based on the computed factuality scores. Additionally, participants increased their trust ratings when relevant sections of the source material were highlighted or responses were annotated with reference numbers corresponding to those sources, compared to when they received no annotation in the source material. Our study offers practical design guidelines to facilitate human-LLM collaboration and it promotes a new human role to carefully evaluate and take responsibility for their use of LLM outputs.

The impressive performances of large language models (LLMs) and their immense potential for commercialization have given rise to serious concerns over the intellectual property (IP) of their training data. In particular, the synthetic texts generated by LLMs may infringe the IP of the data being used to train the LLMs. To this end, it is imperative to be able to (a) identify the data provider who contributed to the generation of a synthetic text by an LLM (source attribution) and (b) verify whether the text data from a data provider has been used to train an LLM (data provenance). In this paper, we show that both problems can be solved by watermarking, i.e., by enabling an LLM to generate synthetic texts with embedded watermarks that contain information about their source(s). We identify the key properties of such watermarking frameworks (e.g., source attribution accuracy, robustness against adversaries), and propose a WAtermarking for Source Attribution (WASA) framework that satisfies these key properties due to our algorithmic designs. Our WASA framework enables an LLM to learn an accurate mapping from the texts of different data providers to their corresponding unique watermarks, which sets the foundation for effective source attribution (and hence data provenance). Extensive empirical evaluations show that our WASA framework achieves effective source attribution and data provenance.

Quotation extraction is a widely useful task both from a sociological and from a Natural Language Processing perspective. However, very little data is available to study this task in languages other than English. In this paper, we present a manually annotated corpus of 1676 newswire texts in French for quotation extraction and source attribution. We first describe the composition of our corpus and the choices that were made in selecting the data. We then detail the annotation guidelines and annotation process, as well as a few statistics about the final corpus and the obtained balance between quote types (direct, indirect and mixed, which are particularly challenging). We end by detailing our inter-annotator agreement between the 8 annotators who worked on manual labelling, which is substantially high for such a difficult linguistic phenomenon.

This paper explores new methods for locating the sources used to write a text, by fine-tuning a variety of language models to rerank candidate sources. After retrieving candidates sources using a baseline BM25 retrieval model, a variety of reranking methods are tested to see how effective they are at the task of source attribution. We conduct experiments on two datasets, English Wikipedia and medieval Arabic historical writing, and employ a variety of retrieval and generation based reranking models. In particular, we seek to understand how the degree of supervision required affects the performance of various reranking models. We find that semisupervised methods can be nearly as effective as fully supervised methods while avoiding potentially costly span-level annotation of the target and source documents.

News articles are driven by the informational sources journalists use in reporting. Modeling when, how and why sources get used together in stories can help us better understand the information we consume and even help journalists with the task of producing it. In this work, we take steps toward this goal by constructing the largest and widest-ranging annotated dataset, to date, of informational sources used in news writing. We show that our dataset can be used to train high-performing models for information detection and source attribution. We further introduce a novel task, source prediction, to study the compositionality of sources in news articles. We show good performance on this task, which we argue is an important proof for narrative science exploring the internal structure of news articles and aiding in planning-based language generation, and an important step towards a source-recommendation system to aid journalists.

Most of us have heard the phrase, "Image is everything." But when it comes to taking AI to the next level, it's context that is everything. Contextual awareness embodies all the subtle nuances of human learning. It is the'who', 'why', 'when', and'why' that inform human decisions and behavior. Without context, the current foundation models are destined to spin their wheels and ultimately interrupt the trajectory of expectation for AI to improve our lives.