Using LLMs to evaluate text, that is, LLM-as-a-judge, is increasingly being used at scale to augment or even replace human annotations. As such, it is imperative that we understand the potential biases and risks of doing so. In this work, we propose an approach for extracting high-level concept-based global policies from LLM-as-a-Judge. Our approach consists of two algorithms: 1) CLoVE (Contrastive Local Verifiable Explanations), which generates verifiable, concept-based, contrastive local explanations and 2) GloVE (Global Verifiable Explanations), which uses iterative clustering, summarization and verification to condense local rules into a global policy. We evaluate GloVE on seven standard benchmarking datasets for content harm detection. We find that the extracted global policies are highly faithful to decisions of the LLM-as-a-Judge. Additionally, we evaluated the robustness of global policies to text perturbations and adversarial attacks. Finally, we conducted a user study to evaluate user understanding and satisfaction with global policies.

Recent advances in Large Language Models (LLMs) and Reinforcement Learning (RL) have led to strong performance in open-domain question answering (QA). However, existing models still struggle with questions that admit multiple valid answers. Standard QA benchmarks, which typically assume a single gold answer, overlook this reality and thus produce inappropriate training signals. Existing attempts to handle ambiguity often rely on costly manual annotation, which is difficult to scale to multi-hop datasets such as HotpotQA and MuSiQue. In this paper, we present A$^2$Search, an annotation-free, end-to-end training framework to recognize and handle ambiguity. At its core is an automated pipeline that detects ambiguous questions and gathers alternative answers via trajectory sampling and evidence verification. The model is then optimized with RL using a carefully designed $\mathrm{AnsF1}$ reward, which naturally accommodates multiple answers. Experiments on eight open-domain QA benchmarks demonstrate that A$^2$Search achieves new state-of-the-art performance. With only a single rollout, A$^2$Search-7B yields an average $\mathrm{AnsF1}@1$ score of $48.4\%$ across four multi-hop benchmarks, outperforming all strong baselines, including the substantially larger ReSearch-32B ($46.2\%$). Extensive analyses further show that A$^2$Search resolves ambiguity and generalizes across benchmarks, highlighting that embracing ambiguity is essential for building more reliable QA systems. Our code, data, and model weights can be found at https://github.com/zfj1998/A2Search

Artificial intelligence has become a part of the provision of governmental services, from making decisions about benefits to issuing fines for parking violations. However, AI systems rarely live up to the promise of neutral optimisation, creating biased or incorrect outputs and reducing the agency of both citizens and civic workers to shape the way decisions are made. Transparency is a principle that can both help subjects understand decisions made about them and shape the processes behind those decisions. However, transparency as practiced around AI systems tends to focus on the production of technical objects that represent algorithmic aspects of decision making. These are often difficult for publics to understand, do not connect to potential for action, and do not give insight into the wider socio-material context of decision making. In this paper, we build on existing approaches that take a human-centric view on AI transparency, combined with a socio-technical systems view, to develop the concept of meaningful transparency for civic AI systems: transparencies that allow publics to engage with AI systems that affect their lives, connecting understanding with potential for action.

High-throughput toxicity testing offers a fast and cost-effective way to test large amounts of compounds. A key component for such systems is the automated evaluation via machine learning models. In this paper, we address critical challenges in this domain and demonstrate how representations learned via self-supervised learning can effectively identify toxicant-induced changes. We provide a proof-of-concept that utilizes the publicly available EmbryoNet dataset, which contains ten zebrafish embryo phenotypes elicited by various chemical compounds targeting different processes in early embryonic development. Our analysis shows that the learned representations using self-supervised learning are suitable for effectively distinguishing between the modes-of-action of different compounds. Finally, we discuss the integration of machine learning models in a physical toxicity testing device in the context of the TOXBOX project.

Abstract: This paper aims to explore two compet ing data science meth odologies to attempt answer ing th e question, " Which issues contributed most to voters' choice in the 2024 presidential election? " The methodologies involve novel empirical evidence driven by artificial intelligence (AI) techniques . By using two distinct methods based on natural language processing and clustering analysis to mine over eight thousand user comments on election - related YouTube videos from one right leaning journal, Wall Street Journal, and one left leaning journal, New York Times, during pre - election week, we quantify the frequency of selected issue areas among user comments to infer which issues were most salient to potential voters in the seven days preceding the November 5th election. Empirically, we primarily demonstrate that immigration and democracy were the most frequently and consistently invoked issues in user comments on the analyzed YouTube videos, followed by the issue of identity politics, while inflation was significantly less frequently referenced. These results corroborate certain findings of post - election surveys but also refute the supposed importance of inflation as an election issue. This indicate s that variations on opinion mining, with their analysis of raw user data online, ca n be more revealing than polling and surveys for analyzing election outcomes. Keywords: artificial intelligence; opinion mining; clustering; vot e choice; cleavages 1. Introduction The Democrats lost both houses of Congress and the Presidency to Republicans in the 2024 election, with former president Donald Trump winning all seven swing states and the national popular vote, despite most pre - election polls giving Vice President Kamala Harris and President Trump a roughly equal chance of winning . Most post - election punditry and analysis in the legacy press and alternative media has attributed the Democrats' large loss to two main issues - inflation [59] and immigration [30] However, a growing contingent of analysts has also attributed the election outcome to the Democratic party's association with cultural issues purportedly distant from the median voter's preferences, such as th ose alternatively aggregated under the concept of "identity" or " woke " politics [54, 56] . To this point, three post - election studies illustrate how voters associated Democrats with left - of - center ideas that were ostensibly distant from most voters' priorities. S urvey research from the think tank Third Way demonstrates that Democrats, and thus Kamala Harris, were largely perceived as "too liberal" [15], while a study from More In Common polling over 5, 000 Americans concluded that while inflation was the top concern for every major demographic group across both parties, Americans misperceived LGBT/transgender policies as the top policy priority for Democrats [37] .

Modeling the dynamics of micro-mobility vehicles (MMV) is becoming increasingly important for training autonomous vehicle systems and building urban traffic simulations. However, mainstream tools rely on variants of the Kinematic Bicycle Model (KBM) or mode-specific physics that miss tire slip, load transfer, and rider/vehicle lean. To our knowledge, no unified, physics-based model captures these dynamics across the full range of common MMVs and wheel layouts. We propose the "Generalized Micro-mobility Model" (GM3), a tire-level formulation based on the tire brush representation that supports arbitrary wheel configurations, including single/double track and multi-wheel platforms. We introduce an interactive model-agnostic simulation framework that decouples vehicle/layout specification from dynamics to compare the GM3 with the KBM and other models, consisting of fixed step RK4 integration, human-in-the-loop and scripted control, real-time trajectory traces and logging for analysis. We also empirically validate the GM3 on the Stanford Drone Dataset's deathCircle (roundabout) scene for biker, skater, and cart classes.

Perception failures in autonomous vehicles (AV) remain a major safety concern because they are the basis for many accidents. To study how these failures affect safety, researchers typically inject artificial faults into hardware or software components and observe the outcomes. However, existing fault injection studies often target a single sensor or machine perception (MP) module, resulting in siloed frameworks that are difficult to generalize or integrate into unified simulation environments. This work addresses that limitation by reframing perception failures as hallucinations, false perceptions that distort an AV situational awareness and may trigger unsafe control actions. Since hallucinations describe only observable effects, this abstraction enables analysis independent of specific sensors or algorithms, focusing instead on how their faults manifest along the MP pipeline. Building on this concept, we propose a configurable, component-agnostic hallucination injection framework that induces six plausible hallucination types in an iterative open-source simulator. More than 18,350 simulations were executed in which hallucinations were injected while AVs crossed an unsignalized transverse street with traffic. The results statistically validate the framework and quantify the impact of each hallucination type on collisions and near misses. Certain hallucinations, such as perceptual latency and drift, significantly increase the risk of collision in the scenario tested, validating the proposed paradigm can stress the AV system safety. The framework offers a scalable, statistically validated, component agnostic, and fully interoperable toolset that simplifies and accelerates AV safety validations, even those with novel MP architectures and components. It can potentially reduce the time-to-market of AV and lay the foundation for future research on fault tolerance, and resilient AV design.

The proliferation of online hate speech poses a significant threat to the harmony of the web. While explicit hate is easily recognized through overt slurs, implicit hate speech is often conveyed through sarcasm, irony, stereotypes, or coded language -- making it harder to detect. Existing hate speech detection models, which predominantly rely on surface-level linguistic cues, fail to generalize effectively across diverse stylistic variations. Moreover, hate speech spread on different platforms often targets distinct groups and adopts unique styles, potentially inducing spurious correlations between them and labels, further challenging current detection approaches. Motivated by these observations, we hypothesize that the generation of hate speech can be modeled as a causal graph involving key factors: contextual environment, creator motivation, target, and style. Guided by this graph, we propose CADET, a causal representation learning framework that disentangles hate speech into interpretable latent factors and then controls confounders, thereby isolating genuine hate intent from superficial linguistic cues. Furthermore, CADET allows counterfactual reasoning by intervening on style within the latent space, naturally guiding the model to robustly identify hate speech in varying forms. CADET demonstrates superior performance in comprehensive experiments, highlighting the potential of causal priors in advancing generalizable hate speech detection.

This paper presents Ryt AI, an LLM-native agentic framework that powers Ryt Bank to enable customers to execute core financial transactions through natural language conversation. This represents the first global regulator-approved deployment worldwide where conversational AI functions as the primary banking interface, in contrast to prior assistants that have been limited to advisory or support roles. Built entirely in-house, Ryt AI is powered by ILMU, a closed-source LLM developed internally, and replaces rigid multi-screen workflows with a single dialogue orchestrated by four LLM-powered agents (Guardrails, Intent, Payment, and FAQ). Each agent attaches a task-specific LoRA adapter to ILMU, which is hosted within the bank's infrastructure to ensure consistent behavior with minimal overhead. Deterministic guardrails, human-in-the-loop confirmation, and a stateless audit architecture provide defense-in-depth for security and compliance. The result is Banking Done Right: demonstrating that regulator-approved natural-language interfaces can reliably support core financial operations under strict governance.

We estimate fair graphs from graph-stationary nodal observations such that connections are not biased with respect to sensitive attributes. Edges in real-world graphs often exhibit preferences for connecting certain pairs of groups. Biased connections can not only exacerbate but even induce unfair treatment for downstream graph-based tasks. We therefore consider group and individual fairness for graphs corresponding to group- and node-level definitions, respectively. To evaluate the fairness of a given graph, we provide multiple bias metrics, including novel measurements in the spectral domain. Furthermore, we propose Fair Spectral Templates (FairSpecTemp), an optimization-based method with two variants for estimating fair graphs from stationary graph signals, a general model for graph data subsuming many existing ones. One variant of FairSpecTemp exploits commutativity properties of graph stationarity while directly constraining bias, while the other implicitly encourages fair estimates by restricting bias in the graph spectrum and is thus more flexible. Our methods enjoy high probability performance bounds, yielding a conditional tradeoff between fairness and accuracy. In particular, our analysis reveals that accuracy need not be sacrificed to recover fair graphs. We evaluate FairSpecTemp on synthetic and real-world data sets to illustrate its effectiveness and highlight the advantages of both variants of FairSpecTemp.