Autoformalization, the process of translating informal statements into formal logic, has gained renewed interest with the emergence of powerful Large Language Models (LLMs). While LLMs show promise in generating structured outputs from natural language (NL), such as Gherkin Scenarios from NL feature requirements, there's currently no formal method to verify if these outputs are accurate. This paper takes a preliminary step toward addressing this gap by exploring the use of a simple LLM-based autoformalizer to verify LLM-generated outputs against a small set of natural language requirements. We conducted two distinct experiments. In the first one, the autoformalizer successfully identified that two differently-worded NL requirements were logically equivalent, demonstrating the pipeline's potential for consistency checks. In the second, the autoformalizer was used to identify a logical inconsistency between a given NL requirement and an LLM-generated output, highlighting its utility as a formal verification tool. Our findings, while limited, suggest that autoformalization holds significant potential for ensuring the fidelity and logical consistency of LLM-generated outputs, laying a crucial foundation for future, more extensive studies into this novel application.

Speech quality and intelligibility are significantly degraded in noisy environments. This paper presents a novel transformer-based learning framework to address the single-channel noise suppression problem for real-time applications. Although existing deep learning networks have shown remarkable improvements in handling stationary noise, their performance often diminishes in real-world environments characterized by non-stationary noise (e.g., dog barking, baby crying). The proposed dual-input acoustic-image feature fusion using a hybrid ViT framework effectively models both temporal and spectral dependencies in noisy signals. Designed for real-world audio environments, the proposed framework is computationally lightweight and suitable for implementation on embedded devices. T o evaluate its effectiveness, four standard and commonly used quality measurements, namely PESQ, STOI, Seg SNR, and LLR, are utilized. Experimental results obtained using the Librispeech dataset as the clean speech source and the Ur-banSound8K and Google Audioset datasets as the noise sources, demonstrate that the proposed method significantly improves noise reduction, speech intelligibility, and perceptual quality compared to the noisy input signal, achieving performance close to the clean reference.

Information extraction from regulatory documents using large language models presents critical trade-offs between performance and computational resources. We evaluated seven open-weight models (0.6B-70B parameters) on hydropower licensing documentation to provide empirical deployment guidance. Our analysis identified a pronounced 14B parameter threshold where validation methods transition from ineffective (F1 $<$ 0.15) to viable (F1 = 0.64). Consumer-deployable models achieve 64\% F1 through appropriate validation, while smaller models plateau at 51\%. Large-scale models approach 77\% F1 but require enterprise infrastructure. We identified systematic hallucination patterns where perfect recall indicates extraction failure rather than success in smaller models. Our findings establish the first comprehensive resource-performance mapping for open-weight information extraction in regulatory contexts, enabling evidence-based model selection. These results provide immediate value for hydropower compliance while contributing insights into parameter scaling effects that generalize across information extraction tasks.

Due to its expressiveness and unambiguous nature, First-Order Logic (FOL) is a powerful formalism for representing concepts expressed in natural language (NL). This is useful, e.g., for specifying and verifying desired system properties. While translating FOL into human-readable English is relatively straightforward, the inverse problem, converting NL to FOL (NL-FOL translation), has remained a longstanding challenge, for both humans and machines. Although the emergence of Large Language Models (LLMs) promised a breakthrough, recent literature provides contrasting results on their ability to perform NL-FOL translation. In this work, we provide a threefold contribution. First, we critically examine existing datasets and protocols for evaluating NL-FOL translation performance, revealing key limitations that may cause a misrepresentation of LLMs' actual capabilities. Second, to overcome these shortcomings, we propose a novel evaluation protocol explicitly designed to distinguish genuine semantic-level logical understanding from superficial pattern recognition, memorization, and dataset contamination. Third, using this new approach, we show that state-of-the-art, dialogue-oriented LLMs demonstrate strong NL-FOL translation skills and a genuine grasp of sentence-level logic, whereas embedding-centric models perform markedly worse.

Language models (LMs) are said to be exhibiting reasoning, but what does this entail? We assess definitions of reasoning and how key papers in the field of natural language processing (NLP) use the notion and argue that the definitions provided are not consistent with how LMs are trained, process information, and generate new tokens. To illustrate this incommensurability we assume the view that transformer-based LMs implement an \textit{implicit} finite-order Markov kernel mapping contexts to conditional token distributions. In this view, reasoning-like outputs correspond to statistical regularities and approximate statistical invariances in the learned kernel rather than the implementation of explicit logical mechanisms. This view is illustrative of the claim that LMs are "statistical pattern matchers"" and not genuine reasoners and provides a perspective that clarifies why reasoning-like outputs arise in LMs without any guarantees of logical consistency. This distinction is fundamental to how epistemic uncertainty is evaluated in LMs. We invite a discussion on the importance of how the computational processes of the systems we build and analyze in NLP research are described.

Large language models are increasingly being used in critical domains of politics, business, and education, but the nature of their normative ethical judgment remains opaque. Alignment research has, to date, not sufficiently utilized perspectives and insights from the field of moral psychology to inform training and evaluation of frontier models. I perform a synthetic experiment on a wide range of models from most major model providers using Jonathan Haidt's influential moral foundations theory (MFT) to elicit diverse value judgments from LLMs. Using multiple descriptive statistical approaches, I document the bias and variance of large language model responses relative to a human baseline in the original survey. My results suggest that models rely on different moral foundations from one another and from a nationally representative human baseline, and these differences increase as model capabilities increase. This work seeks to spur further analysis of LLMs using MFT, including finetuning of open-source models, and greater deliberation by policymakers on the importance of moral foundations for LLM alignment.

Large Language Model (LLM)-based multi-agent systems are increasingly used to simulate human interactions and solve collaborative tasks. A common practice is to assign agents with personas to encourage behavioral diversity. However, this raises a critical yet underexplored question: do personas introduce biases into multi-agent interactions? This paper presents a systematic investigation into persona-induced biases in multi-agent interactions, with a focus on social traits like trustworthiness (how an agent's opinion is received by others) and insistence (how strongly an agent advocates for its opinion). Through a series of controlled experiments in collaborative problem-solving and persuasion tasks, we reveal that (1) LLM-based agents exhibit biases in both trustworthiness and insistence, with personas from historically advantaged groups (e.g., men and White individuals) perceived as less trustworthy and demonstrating less insistence; and (2) agents exhibit significant in-group favoritism, showing a higher tendency to conform to others who share the same persona. These biases persist across various LLMs, group sizes, and numbers of interaction rounds, highlighting an urgent need for awareness and mitigation to ensure the fairness and reliability of multi-agent systems.

The optimal assignment of Large Language Models (LLMs) to specialized roles in multi-agent systems is a significant challenge, defined by a vast combinatorial search space, expensive black-box evaluations, and an inherent trade-off between performance and cost. Current optimization methods focus on single-agent settings and lack a principled framework for this multi-agent, multi-objective problem. This thesis introduces MALBO (Multi-Agent LLM Bayesian Optimization), a systematic framework designed to automate the efficient composition of LLM-based agent teams. We formalize the assignment challenge as a multi-objective optimization problem, aiming to identify the Pareto front of configurations between task accuracy and inference cost. The methodology employs multi-objective Bayesian Optimization (MOBO) with independent Gaussian Process surrogate models. By searching over a continuous feature-space representation of the LLMs, this approach performs a sample-efficient exploration guided by the expected hypervolume improvement. The primary contribution is a principled and automated methodology that yields a Pareto front of optimal team configurations. Our results demonstrate that the Bayesian optimization phase, compared to an initial random search, maintained a comparable average performance while reducing the average configuration cost by over 45%. Furthermore, MALBO identified specialized, heterogeneous teams that achieve cost reductions of up to 65.8% compared to homogeneous baselines, all while maintaining maximum performance. The framework thus provides a data-driven tool for deploying cost-effective and highly specialized multi-agent AI systems.

Recent advances in text-to-image generation have produced strong single-shot models, yet no individual system reliably executes the long, compositional prompts typical of creative workflows. We introduce Image-POSER, a reflective reinforcement learning framework that (i) orchestrates a diverse registry of pretrained text-to-image and image-to-image experts, (ii) handles long-form prompts end-to-end through dynamic task decomposition, and (iii) supervises alignment at each step via structured feedback from a vision-language model critic. By casting image synthesis and editing as a Markov Decision Process, we learn non-trivial expert pipelines that adaptively combine strengths across models. Experiments show that Image-POSER outperforms baselines, including frontier models, across industry-standard and custom benchmarks in alignment, fidelity, and aesthetics, and is consistently preferred in human evaluations. These results highlight that reinforcement learning can endow AI systems with the capacity to autonomously decompose, reorder, and combine visual models, moving towards general-purpose visual assistants.

Generating complex, logically-sound SPARQL queries for multi-hop questions remains a critical bottleneck for Knowledge Graph Question Answering, as the brittle nature of one-shot generation by Large Language Models (LLMs) hinders reliable interaction with structured data. Current methods lack the adaptive policies needed to dynamically debug queries based on real-time execution feedback. This paper introduces a novel agentic framework where an LLM learns a resilient policy for the sequential process of iterative SPARQL construction. We show that a compact 3B-parameter model, trained exclusively via outcome-driven Reinforcement Learning (GRPO) without supervised fine-tuning, can learn effective policies for this task, discovering how to systematically recover from execution errors and refine its queries toward a correct answer. On a curated, executable single-answer subset of LC-QuAD 2.0, our agent achieves 49.7\% accuracy post-entity-linking, a significant 17.5 percentage point improvement over the strongest iterative zero-shot baseline. Further analysis reveals that while the agent's capability is driven by RL, its performance is enhanced by an explicit deliberative reasoning step that acts as a cognitive scaffold to improve policy precision. This work presents a generalizable blueprint for teaching agents to master formal, symbolic tools through interaction, bridging the gap between probabilistic LLMs and the structured world of Knowledge Graphs.