Despite the impressive performance of LLM-powered agents, their adoption for Electronic Health Record (EHR) data access remains limited by the absence of benchmarks that adequately capture real-world clinical data access flows. In practice, two core challenges hinder deployment: query ambiguity from vague user questions and value mismatch between user terminology and database entries. To address this, we introduce EHR-ChatQA an interactive database question answering benchmark that evaluates the end-to-end workflow of database agents: clarifying user questions, using tools to resolve value mismatches, and generating correct SQL to deliver accurate answers. To cover diverse patterns of query ambiguity and value mismatch, EHR-ChatQA assesses agents in a simulated environment with an LLM-based user across two interaction flows: Incremental Query Refinement (IncreQA), where users add constraints to existing queries, and Adaptive Query Refinement (AdaptQA), where users adjust their search goals mid-conversation. Experiments with state-of-the-art LLMs (e.g., o4-mini and Gemini-2.5-Flash) over five i.i.d. trials show that while agents achieve high Pass@5 of 90-95% (at least one of five trials) on IncreQA and 60-80% on AdaptQA, their Pass^5 (consistent success across all five trials) is substantially lower by 35-60%. These results underscore the need to build agents that are not only performant but also robust for the safety-critical EHR domain. Finally, we provide diagnostic insights into common failure modes to guide future agent development.

We introduce Guard Vector, a safety task vector computed as the parameter difference between a guardrail model (Guard Model) and a same-architecture pretrained language model. Composing this vector with a target language model yields a Target Guard Model (TGM). We then adapt TGM with a streaming-aware approach that combines prefix-based training and evaluation with a classifier that produces a single-token output. With this composition alone, TGM improves classification quality over established Guard Models across standard safety suites and enables language extensibility to Chinese, Japanese, and Korean, requiring neither additional training nor target language labels. It also demonstrates model portability across two widely used public guardrail backbones, Llama and Gemma. With prefix SFT (supervised fine-tuning), TGM preserves classification quality under streaming by aligning the behavior between prefix inputs and full-text inputs. The single-token output design increases throughput and reduces latency. Together, these components reduce data and compute requirements while promoting streaming-aware evaluation practices, thereby contributing to a more responsible AI ecosystem.

However, given limited time and computational resources, retraining LLMs to mitigate the influence of undesired data is impractical. Thus, Machine Unlearning (MU) emerges as an alternative solution to weaken a model's performance on undesired knowledge (Liu et al., 2024b; Eldan & Russinovich, 2023) while preserving the model's original utility (Liu et al., 2025). Though much research shed light on MU, several recent studies indicate that MU still lacks robustness (Zhang et al., 2024c; Y uan et al., 2025; Lee et al., 2025). In particular, they are susceptible to both jailbreak attacks (Zou et al., 2023; Andriushchenko et al., 2024) and relearning attacks (Hu et al., 2024). Such limitations can be exploited through reusing small amount of unlearned knowledge (Hu et al., 2024) or adversarial prompt manipulations, including prefix injection (Andriushchenko et al., 2024) and adaptive jailbreaks (Liu et al., 2023). These attacks act as small perturbations in parameter or representation space, driving the model along directions that yield undesired content that should have been forgotten (Fan et al., 2025; Lin et al., 2024b). Smoothness Minimization can be introduced to enhance model robustness against these attacks by promoting a smooth loss across the neighborhood (Foret et al., 2020; Fan et al., 2025). Plenty of studies have sought to remove undesired data to improve the effectiveness of MU and these approaches have demonstrated substantial unlearning performance (Liu et al., 2022a; Thudi et al., 2022; Zou et al., 2024; Pawelczyk et al., 2023; Liu et al., 2024a). However, they still suffer from limitations in robustness and trade-off between model utility and unlearning effectiveness.

The rapid progress of image-to-video (I2V) generation models has introduced significant risks, enabling video synthesis from static images and facilitating deceptive or malicious content creation. While prior defenses such as I2VGuard attempt to immunize images, effective and principled protection to block motion remains underexplored. In this work, we introduce Vid-Freeze - a novel attention-suppressing adversarial attack that adds carefully crafted adversarial perturbations to images. Our method explicitly targets the attention mechanism of I2V models, completely disrupting motion synthesis while preserving semantic fidelity of the input image. The resulting immunized images generate stand-still or near-static videos, effectively blocking malicious content creation. Our experiments demonstrate the impressive protection provided by the proposed approach, highlighting the importance of attention attacks as a promising direction for robust and proactive defenses against misuse of I2V generation models.

Prognostic information is essential for decision-making in breast cancer management. Recently trials have predominantly focused on genomic prognostication tools, even though clinicopathological prognostication is less costly and more widely accessible. Machine learning (ML), transfer learning and ensemble integration offer opportunities to build robust prognostication frameworks. We evaluate this potential to improve survival prognostication in breast cancer by comparing de-novo ML, transfer learning from a pre-trained prognostic tool and ensemble integration. Data from the MA.27 trial was used for model training, with external validation on the TEAM trial and a SEER cohort. Transfer learning was applied by fine-tuning the pre-trained prognostic tool PREDICT v3, de-novo ML included Random Survival Forests and Extreme Gradient Boosting, and ensemble integration was realized through a weighted sum of model predictions. Transfer learning, de-novo RSF, and ensemble integration improved calibration in MA.27 over the pre-trained model (ICI reduced from 0.042 in PREDICT v3 to <=0.007) while discrimination remained comparable (AUC increased from 0.738 in PREDICT v3 to 0.744-0.799). Invalid PREDICT v3 predictions were observed in 23.8-25.8% of MA.27 individuals due to missing information. In contrast, ML models and ensemble integration could predict survival regardless of missing information. Across all models, patient age, nodal status, pathological grading and tumor size had the highest SHAP values, indicating their importance for survival prognostication. External validation in SEER, but not in TEAM, confirmed the benefits of transfer learning, RSF and ensemble integration. This study demonstrates that transfer learning, de-novo RSF, and ensemble integration can improve prognostication in situations where relevant information for PREDICT v3 is lacking or where a dataset shift is likely.

Accurate long-range monsoon rainfall prediction is critical for India's rain-fed agricultural economy and climate resilience planning, yet remains hindered by sparse ground data and complex regional variability. This work proposes a multimodal deep learning framework for gridded precipitation classification using satellite-derived geospatial inputs. Unlike previous rainfall prediction methods relying on coarse-resolution datasets of 5-50 km grid, we curate a high-resolution dataset of projected 1 km grid resolution for five Indian states, integrating seven heterogeneous Earth observation modalities, including land surface temperature, vegetation, soil moisture, humidity, wind speed, elevation, and land use, spanning the June-September 2024 period. We adopt a attention-guided U-Net architecture that captures spatial patterns and temporal dependencies across multi-modalities, and propose a combination of focal and dice loss to address class imbalance and spatial coherence in rainfall categories defined by the India Meteorological Department. Extensive experiments show that the multi-model framework significantly outperforms unimodal baselines and existing deep approaches, especially in underrepresented extreme rainfall zones. The framework demonstrates potential for scalable, region-adaptive monsoon forecasting and Earth observation driven climate risk assessment.

Wikipedia is the largest open knowledge corpus, widely used worldwide and serving as a key resource for training large language models (LLMs) and retrieval-augmented generation (RAG) systems. Ensuring its accuracy is therefore critical. But how accurate is Wikipedia, and how can we improve it? We focus on inconsistencies, a specific type of factual inaccuracy, and introduce the task of corpus-level inconsistency detection. We present CLAIRE, an agentic system that combines LLM reasoning with retrieval to surface potentially inconsistent claims along with contextual evidence for human review. In a user study with experienced Wikipedia editors, 87.5% reported higher confidence when using CLAIRE, and participants identified 64.7% more inconsistencies in the same amount of time. Combining CLAIRE with human annotation, we contribute WIKICOLLIDE, the first benchmark of real Wikipedia inconsistencies. Using random sampling with CLAIRE-assisted analysis, we find that at least 3.3% of English Wikipedia facts contradict another fact, with inconsistencies propagating into 7.3% of FEVEROUS and 4.0% of AmbigQA examples. Benchmarking strong baselines on this dataset reveals substantial headroom: the best fully automated system achieves an AUROC of only 75.1%. Our results show that contradictions are a measurable component of Wikipedia and that LLM-based systems like CLAIRE can provide a practical tool to help editors improve knowledge consistency at scale.

Large language models (LLMs) have demonstrated strong persuasive capabilities comparable to those of humans, offering promising benefits while raising societal concerns about their deployment. However, systematically evaluating the persuasive capabilities of LLMs is inherently challenging, as the effectiveness of persuasion among humans varies significantly across different domains. In this paper, we take a theory-driven approach to provide a scalable and principled framework for measuring the persuasive capabilities of LLMs. Grounded in the Bayesian Persuasion (BP) framework, we repurpose existing human-human persuasion datasets to construct environments for evaluating and training LLMs in strategic persuasion. Our results reveal that frontier models can consistently achieve high persuasion gains and exhibit sophisticated persuasion strategies that align with theoretical predictions. Building on this, we use reinforcement learning to train LLMs for strategic persuasion in our environments. Our results also demonstrate that even small LLMs can obtain significantly higher persuasion gains through reinforcement learning.

Large Language Models (LLMs) vary widely in their capabilities, with larger models often having better performance but higher cost: choosing an LLM model often involves trading off performance and cost. The LLM Cascade is a paradigm that defers difficult queries from weak/cheap to strong/expensive models. This approach is nonadaptive: the deferral decision is trained offline. When confronted with similar or repeated queries, the LLM Cascade may then repeatedly consult the expensive model and incur higher cost. To improve the cascading efficiency, we propose Inter-Cascade, an online and interactive LLM Cascade that extends the role of strong model from a backup helper to a long-term teacher. In our system, when a strong model resolves a difficult query, it also distills its solution into a generalized, reusable problem-solving strategy that boosts the weak model on subsequent queries. Adding strategies to queries enables the weak model to dynamically improve its performance over time, avoiding computationally and time-intensive fine-tuning. Empirically, compared with standard LLM Cascade baselines across multiple benchmarks, the Inter-Cascade significantly improves the accuracy of the weak model (by up to 33.06 absolute percentage points) and the overall system (by up to 5.53 absolute percentage points), while reducing the calls to strong models (by up to 48.05% relative reduction) and saving the corresponding fees (by up to 49.63% relative reduction). Inter-Cascade demonstrates the effective in-context knowledge transfer between LLMs, and provides a general, scalable framework applicable to both open-source and API-based LLMs.

We study a class of multi-stage stochastic programs, which incorporate modeling features from Markov decision processes (MDPs). This class includes structured MDPs with continuous state and action spaces. We extend policy graphs to include decision-dependent uncertainty for one-step transition probabilities as well as a limited form of statistical learning. We focus on the expressiveness of our modeling approach, illustrating ideas with a series of examples of increasing complexity. As a solution method, we develop new variants of stochastic dual dynamic programming, including approximations to handle non-convexities.