arXiv:2605.22672v2 Announce Type: replace Abstract: We document inverse scaling in LLMs on forecasting problems whose underlying time series exhibit superlinear growth and tail risk of regime change, a structure common in finance and epidemiology. On these tasks, more capable models produce worse distributional forecasts. The pattern appears on ForecastBench-Sim (FBSim), a contamination-free, simulated-world benchmark we […]
Retrieval Is Not Enough: Why Organizational AI Needs Epistemic Infrastructure
arXiv:2604.11759v2 Announce Type: replace Abstract: Organizational knowledge used by AI agents typically lacks epistemic structure: retrieval systems surface semantically relevant content without distinguishing binding decisions from abandoned hypotheses, contested claims from settled ones, or known facts from unresolved questions. We argue that the ceiling on organizational AI is not retrieval fidelity but emphepistemic fidelity–the system’s […]
Spectral-inspired Operator Learning with Limited Data and Unknown Physics
arXiv:2505.21573v3 Announce Type: replace-cross Abstract: Learning PDE dynamics from limited data with unknown physics is challenging. Existing neural PDE solvers either require large datasets or rely on known physics (e.g., PDE residuals or handcrafted stencils), leading to limited applicability. To address these challenges, we propose Spectral-Inspired Neural Operator (SINO), which can model complex systems from […]
HARNESS-LM: A Three-Phase Training Recipe for Harnessing SLMs in Sponsored Search Retrieval
arXiv:2605.23572v1 Announce Type: cross Abstract: In the competitive landscape of sponsored search, balancing retrieval quality with production latency is a critical challenge. While large retrieval models based on Small Language Models (SLMs) such as Qwen3-Embedding-4B/8B set strong upper bounds on public benchmarks, their deployment in high-throughput, latency-sensitive environments remains impractical. In this paper, we present […]
Efficient and Transferable Agentic Knowledge Graph RAG via Reinforcement Learning
arXiv:2509.26383v5 Announce Type: replace-cross Abstract: Knowledge-graph retrieval-augmented generation (KG-RAG) couples large language models (LLMs) with structured, verifiable knowledge graphs (KGs) to reduce hallucination and provide reasoning traces. However, current KG-RAG systems often rely on fixed pipelines of multiple LLM modules (e.g., planning, reasoning, and responding), which inflate inference costs and tie performance to specific graph […]
Leveraging Foundation Models for Causal Generative Modeling
arXiv:2605.23861v1 Announce Type: cross Abstract: Causal generative modeling is essential for developing reliable and transparent AI systems capable of counterfactual reasoning. While existing approaches focus on integrating causal constraints during the training of generative models, they often lack a unified framework to leverage the zero-shot reasoning capabilities of pretrained foundation models. We introduce FM-CGM, a […]
DocVAL: Validated Chain-of-Thought Distillation for Grounded Document VQA
arXiv:2511.22521v3 Announce Type: replace-cross Abstract: Document visual question answering requires models not only to answer questions correctly, but also to precisely localize answers within complex document layouts. While large vision-language models (VLMs) achieve strong spatial grounding, their inference cost and latency limit real-world deployment. Compact VLMs are more efficient, but they often suffer substantial localization […]
ROI Extraction in Thermographic Breast Images Using Genetic Algorithms
arXiv:2605.22899v1 Announce Type: new Abstract: This work proposes the use of Genetic Algorithms (GA) to identify the area of the breast from the background in thermographic breast images. The proposed method uses color information, a fitness function based on cardioids, and GA. This is the first work in the literature to propose a Region of […]
Information Access of the Oppressed: Freirean Design for Emancipatory Information Access
arXiv:2601.09600v3 Announce Type: replace-cross Abstract: Online information access (IA) platforms are targets of authoritarian capture. We explore the question of how to safeguard our platforms and ensure emancipatory outcomes through the lens of Paulo Freire’s theories of emancipatory pedagogy. Freire’s theories provide a radically different lens for exploring IA’s sociotechnical concerns relative to the current […]
Towards Trustworthy and Explainable AI for Perception Models: From Concept to Prototype Vehicle Deployment
arXiv:2605.16087v2 Announce Type: replace-cross Abstract: Deep Neural Networks have become the dominant solution for Autonomous Driving perception, but their opacity conflicts with emerging Trustworthy AI guidelines and complicates safety assurance, debugging, and human oversight. While theoretical frameworks for safe and Explainable AI (XAI) exist, concrete implementations of Trustworthy AI for 3D scene understanding remain scarce. […]
On the Infinite Width and Depth Limits of Predictive Coding Networks
arXiv:2602.07697v2 Announce Type: replace-cross Abstract: Predictive coding (PC) is a biologically plausible alternative to standard backpropagation (BP) that minimises an energy function with respect to network activities before updating weights. Recent work has improved the training stability of deep PC networks (PCNs) by leveraging some BP-inspired reparameterisations. However, the full scalability and theoretical basis of […]
Fine-grained Claim-level RAG Benchmark for Law
arXiv:2605.21071v3 Announce Type: replace-cross Abstract: The rapid progress of large language models (LLMs) is shifting semantic search toward a question-answering paradigm, where users ask questions and LLMs generate responses. In high-stake domains such as law, retrieval-augmented generation (RAG) is commonly used to mitigate hallucinations in generated responses. Nonetheless, prior work shows that RAG systems, whether […]