Achieving robust safety alignment in large language models (LLMs) while preserving their utility remains a fundamental challenge. Existing approaches often struggle to balance comprehensive safety with fine-grained controllability at the representation level. We introduce LATENTGUARD, a novel three-stage framework that combines behavioral alignment with supervised latent space control for interpretable and precise safety steering. Our approach begins by fine-tuning an LLM on rationalized datasets containing both reasoning-enhanced refusal responses to adversarial prompts and reasoning-enhanced normal responses to benign queries, establishing robust behavioral priors across both safety-critical and utility-preserving scenarios. We then train a structured variational autoencoder (VAE) on intermediate MLP activations, supervised by multi-label annotations including attack types, attack methods, and benign indicators. This supervision enables the VAE to learn disentangled latent representations that capture distinct adversarial characteristics while maintaining semantic interpretability. Through targeted manipulation of learned latent dimensions, LATENTGUARD achieves selective refusal behavior, effectively blocking harmful requests while preserving helpfulness for legitimate use cases. Experiments on Qwen3-8B demonstrate significant improvements in both safety controllability and response interpretability without compromising utility. Cross-architecture validation on Mistral-7B confirms the generalizability of our latent steering approach, showing consistent effectiveness across different model families. Our results suggest that structured representation-level intervention offers a promising pathway toward building safer yet practical LLM systems.

As LLMs gain adoption in high-stakes domains like mental health, domain experts are increasingly consulted to provide input into policies governing their behavior. From an observation of 19 policymaking workshops with 9 experts over 15 weeks, we identified opportunities to better support rapid experimentation, feedback, and iteration for collaborative policy design processes. We present PolicyPad, an interactive system that facilitates the emerging practice of LLM policy prototyping by drawing from established UX prototyping practices, including heuristic evaluation and storyboarding. Using PolicyPad, policy designers can collaborate on drafting a policy in real time while independently testing policy-informed model behavior with usage scenarios. We evaluate PolicyPad through workshops with 8 groups of 22 domain experts in mental health and law, finding that PolicyPad enhanced collaborative dynamics during policy design, enabled tight feedback loops, and led to novel policy contributions. Overall, our work paves participatory paths for advancing AI alignment and safety.

Patents play a critical role in driving technological innovation by granting inventors exclusive rights to their inventions. However the process of drafting a patent application is often expensive and time-consuming, making it a prime candidate for automation. Despite recent advancements in language models, several challenges hinder the development of robust automated patent drafting systems. First, the information within a patent application is highly confidential, which often prevents the use of closed-source LLMs for automating this task. Second, the process of drafting a patent application is difficult for even the most advanced language models due to their long context, technical writing style, and specialized domain knowledge. To address these challenges, we introduce AutoSpec, a secure, agentic framework for Automatically drafting patent Specification. Our approach decomposes the drafting process into a sequence of manageable subtasks, each solvable by smaller, open-source language models enhanced with custom tools tailored for drafting patent specification. To assess our system, we design a novel evaluation protocol in collaboration with experienced patent attorneys. Our automatic and expert evaluations show that AutoSpec outperforms existing baselines on a patent drafting task.

Multi-agent systems (MAS) are increasingly tasked with solving complex, knowledge-intensive problems where effective agent orchestration is critical. Conventional orchestration methods rely on static agent descriptions, which often become outdated or incomplete. This limitation leads to inefficient task routing, particularly in dynamic environments where agent capabilities continuously evolve. We introduce Knowledge Base-Aware (KBA) Orchestration, a novel approach that augments static descriptions with dynamic, privacy-preserving relevance signals derived from each agent's internal knowledge base (KB). In the proposed framework, when static descriptions are insufficient for a clear routing decision, the orchestrator prompts the subagents in parallel. Each agent then assesses the task's relevance against its private KB, returning a lightweight ACK signal without exposing the underlying data. These collected signals populate a shared semantic cache, providing dynamic indicators of agent suitability for future queries. By combining this novel mechanism with static descriptions, our method achieves more accurate and adaptive task routing preserving agent autonomy and data confidentiality. Benchmarks show that our KBA Orchestration significantly outperforms static description-driven methods in routing precision and overall system efficiency, making it suitable for large-scale systems that require higher accuracy than standard description-driven routing.

This research examines the role of Generative Artificial Intelligence (AI) in enhancing citizen engagement in participatory budgeting. In response to challenges like declining civic participation and increased societal polarization, the study explores how online political participation can strengthen democracy and promote social equity. By integrating Generative AI into public consultation platforms, the research aims to improve citizen proposal formulation and foster effective dialogue between citizens and government. It assesses the capacities governments need to implement AI-enhanced participatory tools, considering technological dependencies and vulnerabilities. Analyzing technological structures, actors, interests, and strategies, the study contributes to understanding how technological advancements can reshape participatory institutions to better facilitate citizen involvement. Ultimately, the research highlights how Generative AI can transform participatory institutions, promoting inclusive, democratic engagement and empowering citizens.

This paper investigates the impact of incorrect data on the performance and safety of large language models (LLMs), specifically gpt-4o, during supervised fine-tuning (SFT). Although LLMs become increasingly vital across broad domains like finance, coding, law, and health, fine-tuning on incorrect data can lead to "emergent misalignment," producing harmful or deceptive outputs unrelated to the intended task. We evaluate gpt-4o models fine-tuned with varying ratios (10\% to 90\% correct) of both obviously and subtly incorrect data across four domains: coding, finance, health, and legal. Our findings show that even modest amounts of incorrect data (10-25\%) dramatically degrade domain performance and not moral alignment. A clear threshold of at least 50\% correct data is needed for models to consistently recover strong performance, though they rarely match the robustness and safety of the base model, which exhibits near-perfect alignment and zero dangerous completions out-of-the-box. This research emphasizes that the cost of incorrect data is heavy, highlighting the critical need for extremely high-quality data curation or, alternatively, leveraging robust base models without unnecessary fine-tuning for high-stakes applications.

AI music generation is rapidly emerging in the creative industries, enabling intuitive music generation from textual descriptions. However, these systems pose risks in exploitation of copyrighted creations, raising ethical and legal concerns. In this paper, we present preliminary results on the first application of machine unlearning techniques from an ongoing research to prevent inadvertent usage of creative content. Particularly, we explore existing methods in machine unlearning to a pre-trained Text-to-Music (TTM) baseline and analyze their efficacy in unlearning pre-trained datasets without harming model performance. Through our experiments, we provide insights into the challenges of applying unlearning in music generation, offering a foundational analysis for future works on the application of unlearning for music generative models.

The Romansh language, spoken in Switzerland, has limited resources for machine translation evaluation. In this paper, we present a benchmark for six varieties of Romansh: Rumantsch Grischun, a supra-regional variety, and five regional varieties: Sursilvan, Sutsilvan, Surmiran, Puter, and Vallader. Our reference translations were created by human translators based on the WMT24++ benchmark, which ensures parallelism with more than 55 other languages. An automatic evaluation of existing MT systems and LLMs shows that translation out of Romansh into German is handled relatively well for all the varieties, but translation into Romansh is still challenging.

Embedding-based similarity metrics between text sequences can be influenced not just by the content dimensions we most care about, but can also be biased by spurious attributes like the text's source or language. These document confounders cause problems for many applications, but especially those that need to pool texts from different corpora. This paper shows that a debiasing algorithm that removes information about observed confounders from the encoder representations substantially reduces these biases at a minimal computational cost. Document similarity and clustering metrics improve across every embedding variant and task we evaluate -- often dramatically. Interestingly, performance on out-of-distribution benchmarks is not impacted, indicating that the embeddings are not otherwise degraded.

A key value proposition of machine learning is generalizability: the same methods and model architecture should be able to work across different domains and different contexts. While powerful, this generalization can sometimes go too far, and miss the importance of the specifics. In this work, we look at how fair machine learning has often treated as interchangeable the identity axis along which discrimination occurs. In other words, racism is measured and mitigated the same way as sexism, as ableism, as ageism. Disciplines outside of computer science have pointed out both the similarities and differences between these different forms of oppression, and in this work we draw out the implications for fair machine learning. While certainly not all aspects of fair machine learning need to be tailored to the specific form of oppression, there is a pressing need for greater attention to such specificity than is currently evident. Ultimately, context specificity can deepen our understanding of how to build more fair systems, widen our scope to include currently overlooked harms, and, almost paradoxically, also help to narrow our scope and counter the fear of an infinite number of group-specific methods of analysis.