This technical report describes the AIA Forecaster, a Large Language Model (LLM)-based system for judgmental forecasting using unstructured data. The AIA Forecaster approach combines three core elements: agentic search over high-quality news sources, a supervisor agent that reconciles disparate forecasts for the same event, and a set of statistical calibration techniques to counter behavioral biases in large language models. On the ForecastBench benchmark (Karger et al., 2024), the AIA Forecaster achieves performance equal to human superforecasters, surpassing prior LLM baselines. In addition to reporting on ForecastBench, we also introduce a more challenging forecasting benchmark sourced from liquid prediction markets. While the AIA Forecaster underperforms market consensus on this benchmark, an ensemble combining AIA Forecaster with market consensus outperforms consensus alone, demonstrating that our forecaster provides additive information. Our work establishes a new state of the art in AI forecasting and provides practical, transferable recommendations for future research. To the best of our knowledge, this is the first work that verifiably achieves expert-level forecasting at scale.

The process includes simulating room and listener acoustic properties (A), modeling talkers' movement trajectories (B), and synthesizing classroom speech mixtures (C). The numbers (1) - (5) correspond to the steps itemized in section II-B more challenging and reflective of classroom acoustics. The separation model is trained to output time-domain waveforms for each speaker with no interference from the other speaker or background noise. This setup enables the model to not only separate overlapping speech, but also to preserve spatial distinctions associated with each moving source. B. Simulation of Overlapping Speech for Classroom Conditions To capture the reverberant and spatial characteristics typical of classroom environments, we developed a spatialization pipeline for generating training and evaluation data (see Fig.1). This pipeline consists of five main components, which are explained below in detail: 1) Simulation of room impulse responses (RIRs) 2) Application of head-related impulse responses (HRIRs) 3) Generation of binaural room impulse responses (BRIRs) 4) Modeling of talkers' movement trajectories 5) Synthesis of the classroom speech data 1) Room Impulse Responses: To simulate naturalistic reverberant classroom acoustics, we generated RIRs that capture direct sound, early reflections, and reverberation or echo. These RIRs were used to spatialize source signals in simulated classroom environments with varying geometry, reverberation, and source-listener distances. We used the Pyroomacoustics Python package [35], which implements the image source method to model sound propagation in rectangular (shoebox) rooms. A total of 30 classrooms were simulated, with dimensions randomly sampled from a range of 8.5 8.5 3 m to 10 10 3.5 m (length width height), reflecting typical U.S. classroom sizes [36], [37].

Current large language models (LLMs) excel in verifiable domains where outputs can be checked before action but prove less reliable for high-stakes strategic decisions with uncertain outcomes. This gap, driven by mutually reinforcing cognitive biases in both humans and artificial intelligence (AI) systems, threatens the defensibility of valuations and sustainability of investments in the sector. This report describes a framework emerging from systematic qualitative assessment across 7 frontier-grade LLMs and 3 market-facing venture vignettes under time pressure. Detailed prompting specifying decision partnership and explicitly instructing avoidance of sycophancy, confabulation, solution drift, and nihilism achieved initial partnership state but failed to maintain it under operational pressure. Sustaining protective partnership state required an emergent 7-stage calibration sequence, built upon a 4-stage initialization process, within a 5-layer protection architecture enabling bias self-monitoring, human-AI adversarial challenge, partnership state verification, performance degradation detection, and stakeholder protection. Three discoveries resulted: partnership state is achievable through ordered calibration but requires emergent maintenance protocols; reliability degrades when architectural drift and context exhaustion align; and dissolution discipline prevents costly pursuit of fundamentally wrong directions. Cross-model validation revealed systematic performance differences across LLM architectures. This approach demonstrates that human-AI teams can achieve cognitive partnership capable of preventing avoidable regret in high-stakes decisions, addressing return-on-investment expectations that depend on AI systems supporting consequential decision-making without introducing preventable cognitive traps when verification arrives too late.

Evaluating answers from state-of-the-art large language models (LLMs) is challenging: lexical metrics miss semantic nuances, whereas "LLM-as-Judge" scoring is computationally expensive. We re-evaluate a lightweight alternative -- off-the-shelf Natural Language Inference (NLI) scoring augmented by a simple lexical-match flag and find that this decades-old technique matches GPT-4o's accuracy (89.9%) on long-form QA, while requiring orders-of-magnitude fewer parameters. To test human alignment of these metrics rigorously, we introduce DIVER-QA, a new 3000-sample human-annotated benchmark spanning five QA datasets and five candidate LLMs. Our results highlight that inexpensive NLI-based evaluation remains competitive and offer DIVER-QA as an open resource for future metric research.

Enterprise relational databases increasingly contain vast amounts of non-semantic data - IP addresses, product identifiers, encoded keys, and timestamps - that challenge traditional semantic analysis. This paper introduces a novel Character-Level Autoencoder (CAE) approach that automatically identifies and groups semantically identical columns in non-semantic relational datasets by detecting column similarities based on data patterns and structures. Unlike conventional Natural Language Processing (NLP) models that struggle with limitations in semantic interpretability and out-of-vocabulary tokens, our approach operates at the character level with fixed dictionary constraints, enabling scalable processing of large-scale data lakes and warehouses. The CAE architecture encodes text representations of non-semantic relational table columns and extracts high-dimensional feature embeddings for data grouping. By maintaining a fixed dictionary size, our method significantly reduces both memory requirements and training time, enabling efficient processing of large-scale industrial data environments. Experimental evaluation demonstrates substantial performance gains: our CAE approach achieved 80.95% accuracy in top 5 column matching tasks across relational datasets, substantially outperforming traditional NLP approaches such as Bag of Words (47.62%). These results demonstrate its effectiveness for identifying and clustering identical columns in relational datasets. This work bridges the gap between theoretical advances in character-level neural architectures and practical enterprise data management challenges, providing an automated solution for schema understanding and data profiling of non-semantic industrial datasets at scale.

Context: The integration of Large Language Models (LLMs) into core software systems is accelerating. However, existing software architecture patterns are static, while current safety assurance methods are not scalable, leaving systems vulnerable to novel adversarial threats. Objective: To design, implement, and evaluate a novel software architecture that enables an AI-driven system to autonomously and continuously adapt its own safety protocols at runtime. Method: We propose the Self-Improving Safety Framework (SISF), a runtime architecture that couples an unprotected, unaligned base LLM (mistralai/Mistral-7B-v0.1) with a dynamic feedback loop. This loop consists of an AI Adjudicator (GPT-4o) for breach detection and a Policy Synthesis Module (GPT-4 Turbo) that autonomously generates new, generalized safety policies (both heuristic and semantic) in response to failures. Results: We conducted a dynamic learning evaluation using the 520-prompt AdvBench dataset. The unprotected model was 100% vulnerable. Our SISF, starting from zero policies, demonstrated a clear learning curve: it detected 237 breaches, autonomously synthesized 234 new policies, and reduced the overall Attack Success Rate (ASR) to 45.58%. In a subsequent test on 520 benign prompts, the SISF achieved a 0.00% False Positive Rate (FPR), proving its ability to adapt without compromising user utility. Conclusion: An architectural approach to AI safety, based on the principles of self-adaptation, is a viable and effective strategy. Our framework demonstrates a practical path towards building more robust, resilient, and scalable AI-driven systems, shifting safety assurance from a static, pre-deployment activity to an automated, runtime process.

Understanding emotional nuances in everyday language is crucial for computational linguistics and emotion research. While traditional lexicon-based tools like LIWC and Pattern have served as foundational instruments, Large Language Models (LLMs) promise enhanced context understanding. We evaluated three Dutch-specific LLMs (ChocoLlama-8B-Instruct, Reynaerde-7B-chat, and GEITje-7B-ultra) against LIWC and Pattern for valence prediction in Flemish, a low-resource language variant. Our dataset comprised approximately 25000 spontaneous textual responses from 102 Dutch-speaking participants, each providing narratives about their current experiences with self-assessed valence ratings (-50 to +50). Surprisingly, despite architectural advancements, the Dutch-tuned LLMs underperformed compared to traditional methods, with Pattern showing superior performance. These findings challenge assumptions about LLM superiority in sentiment analysis tasks and highlight the complexity of capturing emotional valence in spontaneous, real-world narratives. Our results underscore the need for developing culturally and linguistically tailored evaluation frameworks for low-resource language variants, while questioning whether current LLM fine-tuning approaches adequately address the nuanced emotional expressions found in everyday language use.

Retrieval-augmented generation (RAG) enhances large language models (LLMs) by retrieving documents from an external corpus at inference time. When this corpus contains sensitive information, however, unprotected RAG systems are at risk of leaking private information. Prior work has introduced differential privacy (DP) guarantees for RAG, but only in single-query settings, which fall short of realistic usage. In this paper, we study the more practical multi-query setting and propose two DP-RAG algorithms. The first, MURAG, leverages an individual privacy filter so that the accumulated privacy loss only depends on how frequently each document is retrieved rather than the total number of queries. The second, MURAG-ADA, further improves utility by privately releasing query-specific thresholds, enabling more precise selection of relevant documents. Our experiments across multiple LLMs and datasets demonstrate that the proposed methods scale to hundreds of queries within a practical DP budget ($\varepsilon\approx10$), while preserving meaningful utility.

Large Language Models (LLMs) face fundamental challenges in long-context reasoning: many documents exceed their finite context windows, while performance on texts that do fit degrades with sequence length, necessitating their augmentation with external memory frameworks. Current solutions, which have evolved from retrieval using semantic embeddings to more sophisticated structured knowledge graphs representations for improved sense-making and associativity, are tailored for fact-based retrieval and fail to build the space-time-anchored narrative representations required for tracking entities through episodic events. To bridge this gap, we propose the \textbf{Generative Semantic Workspace} (GSW), a neuro-inspired generative memory framework that builds structured, interpretable representations of evolving situations, enabling LLMs to reason over evolving roles, actions, and spatiotemporal contexts. Our framework comprises an \textit{Operator}, which maps incoming observations to intermediate semantic structures, and a \textit{Reconciler}, which integrates these into a persistent workspace that enforces temporal, spatial, and logical coherence. On the Episodic Memory Benchmark (EpBench) \cite{huet_episodic_2025} comprising corpora ranging from 100k to 1M tokens in length, GSW outperforms existing RAG based baselines by up to \textbf{20\%}. Furthermore, GSW is highly efficient, reducing query-time context tokens by \textbf{51\%} compared to the next most token-efficient baseline, reducing inference time costs considerably. More broadly, GSW offers a concrete blueprint for endowing LLMs with human-like episodic memory, paving the way for more capable agents that can reason over long horizons.

Large language models (LLMs) have transformed software development by enabling automated code generation, yet they frequently suffer from systematic errors that limit practical deployment. We identify two critical failure modes: \textit{logical hallucination} (incorrect control/data-flow reasoning) and \textit{schematic hallucination} (type mismatches, signature violations, and architectural inconsistencies). These errors stem from the absence of explicit, queryable representations of repository-wide semantics. This paper presents \textbf{SemanticForge}, which introduces four fundamental algorithmic advances for semantically-aware code generation: (1) a novel automatic reconciliation algorithm for dual static-dynamic knowledge graphs, unifying compile-time and runtime program semantics; (2) a neural approach that learns to generate structured graph queries from natural language, achieving 73\% precision versus 51\% for traditional retrieval; (3) a novel beam search algorithm with integrated SMT solving, enabling real-time constraint verification during generation rather than post-hoc validation; and (4) an incremental maintenance algorithm that updates knowledge graphs in $O(|ΔR| \cdot \log n)$ time while maintaining semantic equivalence.