Compact dual-encoder models are widely used for retrieval owing to their efficiency and scalability. However, such models often underperform compared to their Large Language Model (LLM)-based retrieval counterparts, likely due to their limited world knowledge. While LLM-based data augmentation has been proposed as a strategy to bridge this performance gap, there is insufficient understanding of its effectiveness and scalability to real-world retrieval problems. Existing research does not systematically explore key factors such as the optimal augmentation scale, the necessity of using large augmentation models, and whether diverse augmentations improve generalization, particularly in out-of-distribution (OOD) settings. This work presents a comprehensive study of the effectiveness of LLM augmentation for retrieval, comprising over 100 distinct experimental settings of retrieval models, augmentation models and augmentation strategies. We find that, while augmentation enhances retrieval performance, its benefits diminish beyond a certain augmentation scale, even with diverse augmentation strategies. Surprisingly, we observe that augmentation with smaller LLMs can achieve performance competitive with larger augmentation models. Moreover, we examine how augmentation effectiveness varies with retrieval model pre-training, revealing that augmentation provides the most benefit to models which are not well pre-trained. Our insights pave the way for more judicious and efficient augmentation strategies, thus enabling informed decisions and maximizing retrieval performance while being more cost-effective. Code and augmented datasets accompanying this work are publicly available at https://aka.ms/DAGR.

Empathy is increasingly recognized as a key factor in human-AI communication, yet conventional approaches to "digital empathy" often focus on simulating internal, human-like emotional states while overlooking the inherently subjective, contextual, and relational facets of empathy as perceived by users. In this work, we propose a human-centered taxonomy that emphasizes observable empathic behaviors and introduce a new dataset, Sense-7, of real-world conversations between information workers and Large Language Models (LLMs), which includes per-turn empathy annotations directly from the users, along with user characteristics, and contextual details, offering a more user-grounded representation of empathy. Analysis of 695 conversations from 109 participants reveals that empathy judgments are highly individualized, context-sensitive, and vulnerable to disruption when conversational continuity fails or user expectations go unmet. To promote further research, we provide a subset of 672 anonymized conversation and provide exploratory classification analysis, showing that an LLM-based classifier can recognize 5 levels of empathy with an encouraging average Spearman $ρ$=0.369 and Accuracy=0.487 over this set. Overall, our findings underscore the need for AI designs that dynamically tailor empathic behaviors to user contexts and goals, offering a roadmap for future research and practical development of socially attuned, human-centered artificial agents.

We probe large language models' ability to learn deep form-meaning mappings as defined by construction grammars. We introduce the ConTest-NLI benchmark of 80k sentences covering eight English constructions from highly lexicalized to highly schematic. Our pipeline generates diverse synthetic NLI triples via templating and the application of a model-in-the-loop filter. This provides aspects of human validation to ensure challenge and label reliability. Zero-shot tests on leading LLMs reveal a 24% drop in accuracy between naturalistic (88%) and adversarial data (64%), with schematic patterns proving hardest. Fine-tuning on a subset of ConTest-NLI yields up to 9% improvement, yet our results highlight persistent abstraction gaps in current LLMs and offer a scalable framework for evaluating construction-informed learning.

Building language models (LMs), especially small and medium ones, remains more art than science. While large LMs often improve by sheer scale, it is still unclear why many design choices work. For small LMs, this uncertainty is more limiting: tight parameter budgets make each decision critical, yet researchers still lack systematic, scientific ways to test and refine new ideas. We introduce Pico, a lightweight, modular framework that enables systematic, hypothesis-driven research for small and medium-scale language model development. Pico consists of two libraries that together provide a practical sandbox where researchers can make targeted changes to a model's architecture or training procedures and directly observe their effects on the model's behavior. To support reproducible experimentation, we also release a suite of baseline models, pico-decoder, trained under standardized conditions and open-sourced for the community. Case studies highlight how Pico can support iterative small LM design and analysis.

Large Language Models (LLMs) are increasingly involved in high-stakes domains, yet how they reason about socially sensitive decisions remains underexplored. We present a large-scale audit of LLMs' treatment of socioeconomic status (SES) in college admissions decisions using a novel dual-process framework inspired by cognitive science. Leveraging a synthetic dataset of 30,000 applicant profiles grounded in real-world correlations, we prompt 4 open-source LLMs (Qwen 2, Mistral v0.3, Gemma 2, Llama 3.1) under 2 modes: a fast, decision-only setup (System 1) and a slower, explanation-based setup (System 2). Results from 5 million prompts reveal that LLMs consistently favor low-SES applicants -- even when controlling for academic performance -- and that System 2 amplifies this tendency by explicitly invoking SES as compensatory justification, highlighting both their potential and volatility as decision-makers. We then propose DPAF, a dual-process audit framework to probe LLMs' reasoning behaviors in sensitive applications.

Accurate and reliable knowledge retrieval is vital for financial question-answering, where continually updated data sources and complex, high-stakes contexts demand precision. Traditional retrieval systems rely on a single database and retriever, but financial applications require more sophisticated approaches to handle intricate regulatory filings, market analyses, and extensive multi-year reports. We introduce a framework for financial Retrieval Augmented Generation (RAG) that leverages agentic AI and the Multi-HyDE system, an approach that generates multiple, nonequivalent queries to boost the effectiveness and coverage of retrieval from large, structured financial corpora. Our pipeline is optimized for token efficiency and multi-step financial reasoning, and we demonstrate that their combination improves accuracy by 11.2% and reduces hallucinations by 15%. Our method is evaluated on standard financial QA benchmarks, showing that integrating domain-specific retrieval mechanisms such as Multi-HyDE with robust toolsets, including keyword and table-based retrieval, significantly enhances both the accuracy and reliability of answers. This research not only delivers a modular, adaptable retrieval framework for finance but also highlights the importance of structured agent workflows and multi-perspective retrieval for trustworthy deployment of AI in high-stakes financial applications.

Abstract-- Robot assistive navigation (RAN) is critical for enhancing the mobility and independence of the growing population of mobility-impaired individuals. However, existing systems often rely on interfaces that fail to replicate the intuitive and efficient physical communication observed between a person and a human caregiver, limiting their effectiveness. In this paper, we introduce T ac-Nav, a RAN system that leverages a cylindrical tactile skin mounted on a Stretch 3 mobile manipulator to provide a more natural and efficient interface for human navigational intent recognition. T o robustly classify the tactile data, we developed the Cylindrical Kernel Support V ector Machine (CK-SVM), an algorithm that explicitly models the sensor's cylindrical geometry and is consequently robust to the natural rotational shifts present in a user's grasp. Comprehensive experiments were conducted to demonstrate the effectiveness of our classification algorithm and the overall system. Results show that CK-SVM achieved superior classification accuracy on both simulated (97.1%) and real-world (90.8%) datasets compared to four baseline models. Furthermore, a pilot study confirmed that users more preferred the T ac-Nav tactile interface over conventional joystick and voice-based controls. I. INTRODUCTION Robot assistive navigation (RAN) - the task of a robot providing physical support while people moving from one place to another - is of critical importance for people with mobility impairments [1]. In the U.S., 12.2% of adults live with a mobility disability, and the aging population suggests an increasing need for navigation assistance [2], [3].

Integration and analysis of multi-omics data provide valuable insights for cancer subtype classification. However, such data are inherently heterogeneous, high-dimensional, and exhibit complex intra- and inter-modality dependencies. Recent advances in graph neural networks (GNNs) offer powerful tools for modeling such structure. Yet, most existing methods rely on prior knowledge or predefined similarity networks to construct graphs, which are often undirected or unweighted, failing to capture the directionality and strength of biological interactions. Interpretability at both the modality and feature levels also remains limited. To address these challenges, we propose TF-DWGNet, a novel Graph Neural Network framework that combines tree-based Directed Weighted graph construction with Tensor Fusion for multiclass cancer subtype classification. TF-DWGNet introduces two key innovations: a supervised tree-based approach for constructing directed, weighted graphs tailored to each omics modality, and a tensor fusion mechanism that captures unimodal, bimodal, and trimodal interactions using low-rank decomposition for efficiency. TF-DWGNet enables modality-specific representation learning, joint embedding fusion, and interpretable subtype prediction. Experiments on real-world cancer datasets show that TF-DWGNet consistently outperforms state-of-the-art baselines across multiple metrics and statistical tests. Moreover, it provides biologically meaningful insights by ranking influential features and modalities. These results highlight TF-DWGNet's potential for effective and interpretable multi-omics integration in cancer research.

There is an increasing imperative to integrate programming platforms within AI frameworks to enhance educational tasks for both teachers and students. However, commonly used platforms such as Code.org, Scratch, and Snap fall short of providing the desired AI features and lack adaptability for interdisciplinary applications. This study explores how educational platforms can be improved by incorporating AI and analytics features to create more effective learning environments across various subjects and domains. We interviewed 8 K-12 teachers and asked their practices and needs while using any block-based programming (BBP) platform in their classes. We asked for their approaches in assessment, course development and expansion of resources, and student monitoring in their classes. Thematic analysis of the interview transcripts revealed both commonalities and differences in the AI tools needed between the STEM and non-STEM groups. Our results indicated advanced AI features that could promote BBP platforms. Both groups stressed the need for integrity and plagiarism checks, AI adaptability, customized rubrics, and detailed feedback in assessments. Non-STEM teachers also emphasized the importance of creative assignments and qualitative assessments. Regarding resource development, both AI tools desired for updating curricula, tutoring libraries, and generative AI features. Non-STEM teachers were particularly interested in supporting creative endeavors, such as art simulations. For student monitoring, both groups prioritized desktop control, daily tracking, behavior monitoring, and distraction prevention tools. Our findings identify specific AI-enhanced features needed by K-12 teachers across various disciplines and lay the foundation for creating more efficient, personalized, and engaging educational experiences.

Virtual screening (VS) aims to identify bioactive compounds from vast chemical libraries, but remains difficult in low-label regimes where only a few actives are known. Existing methods largely rely on general-purpose molecular fingerprints and overlook class-discriminative substructures critical to bioactivity. Moreover, they consider molecules independently, limiting effectiveness in low-label regimes. We introduce SubDyve, a network-based VS framework that constructs a subgraph-aware similarity network and propagates activity signals from a small known actives. When few active compounds are available, SubDyve performs iterative seed refinement, incrementally promoting new candidates based on local false discovery rate. This strategy expands the seed set with promising candidates while controlling false positives from topological bias and overexpansion. We evaluate SubDyve on ten DUD-E targets under zero-shot conditions and on the CDK7 target with a 10-million-compound ZINC dataset. SubDyve consistently outperforms existing fingerprint or embedding-based approaches, achieving margins of up to +34.0 on the BEDROC and +24.6 on the EF1% metric.