Patent drafting presents significant challenges due to its reliance on the extensive experience and specialized expertise of patent attorneys, who must possess both legal acumen and technical understanding of an invention to craft patent applications in a formal legal writing style. This paper presents a demonstration of Patentformer, an AI-powered automated patent drafting platform designed to support patent attorneys by rapidly producing high-quality patent applications adhering to legal writing standards.

In this paper, we introduce Narrative Learning, a methodology where models are defined entirely in natural language and iteratively refine their classification criteria using explanatory prompts rather than traditional numerical optimisation. We report on experiments to evaluate the accuracy and potential of this approach using 3 synthetic and 3 natural datasets and compare them against 7 baseline explainable machine learning models. We demonstrate that on 5 out of 6 of these datasets, Narrative Learning became more accurate than the baseline explainable models in 2025 or earlier because of improvements in language models. We also report on trends in the lexicostatistics of these models' outputs as a proxy for the comprehensibility of the explanations.

Large models (LMs) are powerful content generators, yet their open-ended nature can also introduce potential risks, such as generating harmful or biased content. Existing guardrails mostly perform post-hoc detection that may expose unsafe content before it is caught, and the latency constraints further push them toward lightweight models, limiting detection accuracy. In this work, we propose Kelp, a novel plug-in framework that enables streaming risk detection within the LM generation pipeline. Kelp leverages intermediate LM hidden states through a Streaming Latent Dynamics Head (SLD), which models the temporal evolution of risk across the generated sequence for more accurate real-time risk detection. To ensure reliable streaming moderation in real applications, we introduce an Anchored Temporal Consistency (ATC) loss to enforce monotonic harm predictions by embedding a benign-then-harmful temporal prior. Besides, for a rigorous evaluation of streaming guardrails, we also present StreamGuardBench-a model-grounded benchmark featuring on-the-fly responses from each protected model, reflecting real-world streaming scenarios in both text and vision-language tasks. Across diverse models and datasets, Kelp consistently outperforms state-of-the-art post-hoc guardrails and prior plug-in probes (15.61% higher average F1), while using only 20M parameters and adding less than 0.5 ms of per-token latency.

Federated learning is distributed model training across several clients without disclosing raw data. Despite advancements in data privacy, risks still remain. Differential Privacy (DP) is a technique to protect sensitive data by adding noise to model updates, usually controlled by a fixed privacy budget. However, this approach can introduce excessive noise, particularly when the model converges, which compromises performance. To address this problem, adaptive privacy budgets have been investigated as a potential solution. This work implements DP methods using Laplace and Gaussian mechanisms with an adaptive privacy budget, extending the SelecEval simulator. We introduce an adaptive clipping approach in the Gaussian mechanism, ensuring that gradients of the model are dynamically updated rather than using a fixed sensitivity. We conduct extensive experiments with various privacy budgets, IID and non-IID datasets, and different numbers of selected clients per round. While our experiments were limited to 200 training rounds, the results suggest that adaptive privacy budgets and adaptive clipping can help maintain model accuracy while preserving privacy.

Every year, the European Union and its member states allocate millions of euros to fund various development initiatives. However, the increasing number of applications received for these programs often creates significant bottlenecks in evaluation processes, due to limited human capacity. In this work, we detail the real-world deployment of AI-assisted evaluation within the pipeline of two government initiatives: (i) corporate applications aimed at international business expansion, and (ii) citizen reimbursement claims for investments in energy-efficient home improvements. While these two cases involve distinct evaluation procedures, our findings confirm that AI effectively enhanced processing efficiency and reduced workload across both types of applications. Specifically, in the citizen reimbursement claims initiative, our solution increased reviewer productivity by 20.1%, while keeping a negligible false-positive rate based on our test set observations. These improvements resulted in an overall reduction of more than 2 months in the total evaluation time, illustrating the impact of AI-driven automation in large-scale evaluation workflows.

We address the problem of auditing whether sensitive or copyrighted texts were used to fine-tune large language models (LLMs) under black-box access. Prior signals-verbatim regurgitation and membership inference-are unreliable at the level of individual documents or require altering the visible text. We introduce a text-preserving watermarking framework that embeds sequences of invisible Unicode characters into documents. Each watermark is split into a cue (embedded in odd chunks) and a reply (embedded in even chunks). At audit time, we submit prompts that contain only the cue; the presence of the corresponding reply in the model's output provides evidence of memorization consistent with training on the marked text. To obtain sound decisions, we compare the score of the published watermark against a held-out set of counterfactual watermarks and apply a ranking test with a provable false-positive-rate bound. The design is (i) minimally invasive (no visible text changes), (ii) scalable to many users and documents via a large watermark space and multi-watermark attribution, and (iii) robust to common passive transformations. We evaluate on open-weight LLMs and multiple text domains, analyzing regurgitation dynamics, sensitivity to training set size, and interference under multiple concurrent watermarks. Our results demonstrate reliable post-hoc provenance signals with bounded FPR under black-box access. We experimentally observe a failure rate of less than 0.1\% when detecting a reply after fine-tuning with 50 marked documents. Conversely, no spurious reply was recovered in over 18,000 challenges, corresponding to a 100\%TPR@0\% FPR. Moreover, detection rates remain relatively stable as the dataset size increases, maintaining a per-document detection rate above 45\% even when the marked collection accounts for less than 0.33\% of the fine-tuning data.

The excitement brought by the development of AI agents came alongside arising problems. These concerns centered around users' trust issues towards AIs, the risks involved, and the difficulty of attributing responsibilities and liabilities. Current solutions only attempt to target each problem separately without acknowledging their inter-influential nature. The Trust, Risk and Liability (TRL) framework proposed in this paper, however, ties together the interdependent relationships of trust, risk, and liability to provide a systematic method of building and enhancing trust, analyzing and mitigating risks, and allocating and attributing liabilities. It can be applied to analyze any application scenarios of AI agents and suggest appropriate measures fitting to the context. The implications of the TRL framework lie in its potential societal impacts, economic impacts, ethical impacts, and more. It is expected to bring remarkable values to addressing potential challenges and promoting trustworthy, risk-free, and responsible usage of AI in 6G networks.

Retrieval-Augmented Generation (RAG) integrates large language models (LLMs) with external sources, but unresolved contradictions in retrieved evidence often lead to hallucinations and legally unsound outputs. Benchmarks currently used for contradiction detection lack domain realism, cover only limited conflict types, and rarely extend beyond single-sentence pairs, making them unsuitable for legal applications. Controlled generation of documents with embedded contradictions is therefore essential: it enables systematic stress-testing of models, ensures coverage of diverse conflict categories, and provides a reliable basis for evaluating contradiction detection and resolution. We present a multi-agent contradiction-aware benchmark framework for the legal domain that generates synthetic legal-style documents, injects six structured contradiction types, and models both self- and pairwise inconsistencies. Automated contradiction mining is combined with human-in-the-loop validation to guarantee plausibility and fidelity. This benchmark offers one of the first structured resources for contradiction-aware evaluation in legal RAG pipelines, supporting more consistent, interpretable, and trustworthy systems.

As governments move to regulate AI, there is growing interest in using Large Language Models (LLMs) to assess whether or not an AI system complies with a given AI Regulation (AIR). However, there is presently no way to benchmark the performance of LLMs at this task. To fill this void, we introduce AIReg-Bench: the first benchmark dataset designed to test how well LLMs can assess compliance with the EU AI Act (AIA). We created this dataset through a two-step process: (1) by prompting an LLM with carefully structured instructions, we generated 120 technical documentation excerpts (samples), each depicting a fictional, albeit plausible, AI system - of the kind an AI provider might produce to demonstrate their compliance with AIR; (2) legal experts then reviewed and annotated each sample to indicate whether, and in what way, the AI system described therein violates specific Articles of the AIA. The resulting dataset, together with our evaluation of whether frontier LLMs can reproduce the experts' compliance labels, provides a starting point to understand the opportunities and limitations of LLM-based AIR compliance assessment tools and establishes a benchmark against which subsequent LLMs can be compared. The dataset and evaluation code are available at https://github.com/camlsys/aireg-bench.

Large Language Models (LLMs) are widely used in industry but remain prone to hallucinations, limiting their reliability in critical applications. This work addresses hallucination reduction in consumer grievance chatbots built using LLaMA 3.1 8B Instruct, a compact model frequently used in industry. We develop HalluDetect, an LLM-based hallucination detection system that achieves an F1 score of 68.92% outperforming baseline detectors by 22.47%. Benchmarking five hallucination mitigation architectures, we find that out of them, AgentBot minimizes hallucinations to 0.4159 per turn while maintaining the highest token accuracy (96.13%), making it the most effective mitigation strategy. Our findings provide a scalable framework for hallucination mitigation, demonstrating that optimized inference strategies can significantly improve factual accuracy.