Large language models (LLMs) are increasingly integrated into real-world applications through retrieval-augmented generation (RAG) mechanisms to supplement their responses with up-to-date and domain-specific knowledge. However, the valuable and often proprietary nature of the knowledge bases used in RAG introduces the risk of unauthorized usage by adversaries. Existing methods that can be generalized as watermarking techniques to protect these knowledge bases typically involve poisoning attacks. However, these methods require to alter the results of verification samples (\eg, generating incorrect outputs), inevitably making them susceptible to anomaly detection and even introduce new security risks. To address these challenges, we propose \name{} for `harmless' copyright protection of knowledge bases. Instead of manipulating LLM's final output, \name{} implants distinct verification behaviors in the space of chain-of-thought (CoT) reasoning, maintaining the correctness of the final answer. Our method has three main stages: (1) \textbf{Generating CoTs}: For each verification question, we generate two CoTs, including a target CoT for building watermark behaviors; (2) \textbf{Optimizing Watermark Phrases and Target CoTs}: We optimize them to minimize retrieval errors under the black-box setting of suspicious LLM, ensuring that the watermarked verification queries activate the target CoTs without being activated in non-watermarked ones; (3) \textbf{Ownership Verification}: We exploit a pairwise Wilcoxon test to statistically verify whether a suspicious LLM is augmented with the protected knowledge base by comparing its responses to watermarked and benign verification queries. Our experiments on diverse benchmarks demonstrate that \name{} effectively protects knowledge bases against unauthorized usage while preserving the integrity and performance of the RAG.

Advanced Persistent Threats (APTs) pose a significant security risk to organizations and industries. These attacks often lead to severe data breaches and compromise the system for a long time. Mitigating these sophisticated attacks is highly challenging due to the stealthy and persistent nature of APTs. Machine learning models are often employed to tackle this challenge by bringing automation and scalability to APT detection. Nevertheless, these intelligent methods are data-driven, and thus, highly affected by the quality and relevance of input data. This paper aims to analyze measurements considered when recording network traffic and conclude which features contribute more to detecting APT samples. To do this, we study the features associated with various APT cases and determine their importance using a machine learning framework. To ensure the generalization of our findings, several feature selection techniques are employed and paired with different classifiers to evaluate their effectiveness. Our findings provide insights into how APT detection can be enhanced in real-world scenarios.

Detecting factual inconsistency for long document summarization remains challenging, given the complex structure of the source article and long summary length. In this work, we study factual inconsistency errors and connect them with a line of discourse analysis. We find that errors are more common in complex sentences and are associated with several discourse features. We propose a framework that decomposes long texts into discourse-inspired chunks and utilizes discourse information to better aggregate sentence-level scores predicted by natural language inference models. Our approach shows improved performance on top of different model baselines over several evaluation benchmarks, covering rich domains of texts, focusing on long document summarization. This underscores the significance of incorporating discourse features in developing models for scoring summaries for long document factual inconsistency.

Assessing the novelty of patent claims is a critical yet challenging task traditionally performed by patent examiners. While advancements in NLP have enabled progress in various patent-related tasks, novelty assessment remains unexplored. This paper introduces a novel challenge by evaluating the ability of large language models (LLMs) to assess patent novelty by comparing claims with cited prior art documents, following the process similar to that of patent examiners done. We present the first dataset specifically designed for novelty evaluation, derived from real patent examination cases, and analyze the capabilities of LLMs to address this task. Our study reveals that while classification models struggle to effectively assess novelty, generative models make predictions with a reasonable level of accuracy, and their explanations are accurate enough to understand the relationship between the target patent and prior art. These findings demonstrate the potential of LLMs to assist in patent evaluation, reducing the workload for both examiners and applicants. Our contributions highlight the limitations of current models and provide a foundation for improving AI-driven patent analysis through advanced models and refined datasets.

We study an online dynamic pricing problem where the potential demand at each time period $t=1,2,\ldots, T$ is stochastic and dependent on the price. However, a perishable inventory is imposed at the beginning of each time $t$, censoring the potential demand if it exceeds the inventory level. To address this problem, we introduce a pricing algorithm based on the optimistic estimates of derivatives. We show that our algorithm achieves $\tilde{O}(\sqrt{T})$ optimal regret even with adversarial inventory series. Our findings advance the state-of-the-art in online decision-making problems with censored feedback, offering a theoretically optimal solution against adversarial observations.

We propose a new long-context financial benchmark, FailSafeQA, designed to test the robustness and context-awareness of LLMs against six variations in human-interface interactions in LLM-based query-answer systems within finance. We concentrate on two case studies: Query Failure and Context Failure. In the Query Failure scenario, we perturb the original query to vary in domain expertise, completeness, and linguistic accuracy. In the Context Failure case, we simulate the uploads of degraded, irrelevant, and empty documents. We employ the LLM-as-a-Judge methodology with Qwen2.5-72B-Instruct and use fine-grained rating criteria to define and calculate Robustness, Context Grounding, and Compliance scores for 24 off-the-shelf models. The results suggest that although some models excel at mitigating input perturbations, they must balance robust answering with the ability to refrain from hallucinating. Notably, Palmyra-Fin-128k-Instruct, recognized as the most compliant model, maintained strong baseline performance but encountered challenges in sustaining robust predictions in 17% of test cases. On the other hand, the most robust model, OpenAI o3-mini, fabricated information in 41% of tested cases. The results demonstrate that even high-performing models have significant room for improvement and highlight the role of FailSafeQA as a tool for developing LLMs optimized for dependability in financial applications. The dataset is available at: https://huggingface.co/datasets/Writer/FailSafeQA

The recent surge in high-quality open-sourced Generative AI text models (colloquially: LLMs), as well as efficient finetuning techniques, has opened the possibility of creating high-quality personalized models, i.e., models generating text attuned to a specific individual's needs and capable of credibly imitating their writing style by leveraging that person's own data to refine an open-source model. The technology to create such models is accessible to private individuals, and training and running such models can be done cheaply on consumer-grade hardware. These advancements are a huge gain for usability and privacy. This position paper argues, however, that these advancements also introduce new safety risks by making it practically feasible for malicious actors to impersonate specific individuals at scale, for instance for the purpose of phishing emails, based on small amounts of publicly available text. We further argue that these risks are complementary to - and distinct from - the much-discussed risks of other impersonation attacks such as image, voice, or video deepfakes, and are not adequately addressed by the larger research community, or the current generation of open - and closed-source models.

Rajesh Ranjan* (Carnegie Mellon University, USA) Shailja Gupta* (Carnegie Mellon University, USA) Surya Narayan Singh* (BIT Sindri, India) Abstract: Ensuring fairness in decentralized multi-agent systems presents significant challenges due to emergent biases, systemic inefficiencies, and conflicting agent incentives. This paper provides a comprehensive survey of fairness in multi-agent AI, introducing a novel framework where fairness is treated as a dynamic, emergent property of agent interactions. The framework integrates fairness constraints, bias mitigation strategies, and incentive mechanisms to align autonomous agent behaviors with societal values while balancing efficiency and robustness. Through empirical validation, we demonstrate that incorporating fairness constraints results in more equitable decision-making. Introduction As artificial intelligence (AI) systems evolve, Agentic AI --autonomous systems capable of independent decision-making and goal-setting--has emerged as a ...

Debating over conflicting issues is a necessary first step towards resolving conflicts. However, intrinsic perspectives of an arguer are difficult to overcome by persuasive argumentation skills. Proceeding from a debate to a deliberative process, where we can identify actionable options for resolving a conflict requires a deeper analysis of arguments and the perspectives they are grounded in - as it is only from there that one can derive mutually agreeable resolution steps. In this work we develop a framework for a deliberative analysis of arguments in a computational argumentation setup. We conduct a fine-grained analysis of perspectivized stances expressed in the arguments of different arguers or stakeholders on a given issue, aiming not only to identify their opposing views, but also shared perspectives arising from their attitudes, values or needs. We formalize this analysis in Perspectivized Stance Vectors that characterize the individual perspectivized stances of all arguers on a given issue. We construct these vectors by determining issue- and argument-specific concepts, and predict an arguer's stance relative to each of them. The vectors allow us to measure a modulated (dis)agreement between arguers, structured by perspectives, which allows us to identify actionable points for conflict resolution, as a first step towards deliberation.

Recent work has demonstrated the effectiveness of formulating decision making as supervised learning on offline-collected trajectories. Powerful sequence models, such as GPT or BERT, are often employed to encode the trajectories. However, the benefits of performing sequence modeling on trajectory data remain unclear. In this work, we investigate whether sequence modeling has the ability to condense trajectories into useful representations that enhance policy learning. We adopt a two-stage framework that first leverages sequence models to encode trajectory-level representations, and then learns a goal-conditioned policy employing the encoded representations as its input.