Prompt-based reasoning strategies such as Chain-of-Thought (CoT) and In-Context Learning (ICL) have become widely used for eliciting reasoning capabilities in large language models (LLMs). However, these methods rely on fragile, implicit mechanisms often yielding inconsistent outputs across seeds, formats, or minor prompt variations making them fundamentally unreliable for tasks requiring stable, interpretable reasoning. In contrast, automata-based neuro-symbolic frameworks like RetoMaton offer a more structured and trustworthy alternative by grounding retrieval in symbolic memory with deterministic transitions. In this work, we extend RetoMaton by replacing its global datastore with a local, task-adaptive Weighted Finite Automaton (WFA), constructed directly from external domain corpora. This local automaton structure promotes robust, context-aware retrieval while preserving symbolic traceability and low inference overhead. Unlike prompting, which entangles context and memory in opaque ways, our approach leverages the explicit structure of WFAs to provide verifiable and modular retrieval behavior, making it better suited for domain transfer and interoperability. We evaluate this local RetoMaton variant on two pretrained LLMs LLaMA-3.2-1B and Gemma-3-1B-PT across three reasoning tasks: TriviaQA (reading comprehension), GSM8K (multi-step math), and MMLU (domain knowledge). Compared to the base model and prompting-based methods, augmenting these setups with local RetoMaton consistently improves performance while enabling transparent and reproducible retrieval dynamics. Our results highlight a promising shift toward trustworthy, symbolic reasoning in modern LLMs via lightweight, automaton-guided memory.

Large language models (LLMs) are often trained on data that reflect WEIRD values: Western, Educated, Industrialized, Rich, and Democratic. This raises concerns about cultural bias and fairness. Using responses to the World Values Survey, we evaluated five widely used LLMs: GPT-3.5, GPT-4, Llama-3, BLOOM, and Qwen. We measured how closely these responses aligned with the values of the WEIRD countries and whether they conflicted with human rights principles. To reflect global diversity, we compared the results with the Universal Declaration of Human Rights and three regional charters from Asia, the Middle East, and Africa. Models with lower alignment to WEIRD values, such as BLOOM and Qwen, produced more culturally varied responses but were 2% to 4% more likely to generate outputs that violated human rights, especially regarding gender and equality. For example, some models agreed with the statements ``a man who cannot father children is not a real man'' and ``a husband should always know where his wife is'', reflecting harmful gender norms. These findings suggest that as cultural representation in LLMs increases, so does the risk of reproducing discriminatory beliefs. Approaches such as Constitutional AI, which could embed human rights principles into model behavior, may only partly help resolve this tension.

The accelerated evolution of large language models has raised questions about their comparative performance across domains of practical importance. GPT-4 by OpenAI introduced advances in reasoning, multimodality, and task generalization, establishing itself as a valuable tool in education, clinical diagnosis, and academic writing, though it was accompanied by several flaws. Released in August 2025, GPT-5 incorporates a system-of-models architecture designed for task-specific optimization and, based on both anecdotal accounts and emerging evidence from the literature, demonstrates stronger performance than its predecessor in medical contexts. This study provides one of the first systematic comparisons of GPT-4 and GPT-5 using human raters from linguistics and clinical fields. Twenty experts evaluated model-generated outputs across five domains: lesson planning, assignment evaluation, clinical diagnosis, research generation, and ethical reasoning, based on predefined criteria. Mixed-effects models revealed that GPT-5 significantly outperformed GPT-4 in lesson planning, clinical diagnosis, research generation, and ethical reasoning, while both models performed comparably in assignment assessment. The findings highlight the potential of GPT-5 to serve as a context-sensitive and domain-specialized tool, offering tangible benefits for education, clinical practice, and academic research, while also advancing ethical reasoning. These results contribute to one of the earliest empirical evaluations of the evolving capabilities and practical promise of GPT-5.

However, this approach suffers from two major drawbacks. First, current PRMs typically function as "black-box" classifiers, providing a score or label without explaining why a step is correct or flawed. Second, their reliance on supervised fine-tuning (SFT) with static datasets can limit their ability to generalize to new reasoning patterns (Lightman et al., 2023; Luo et al., 2024; Wang et al., 2023; Xiong et al., 2024b; Zhang et al., 2024a). We conduct a comprehensive evaluation of our method across three key dimensions: (i) the judge's To improve the reliability of multi-step reasoning in LLMs, one can consider methods beyond evaluating only the final answer, termed Outcome Reward Models (ORMs), by instead evaluating each intermediate step, a method pioneered by Process Reward Models (PRMs). Subsequent research has focused on automating this annotation process. Wang et al. (2023) proposed Concurrent work by He et al. (2025) uses a prompting approach to segment thought process into This involves replacing the language model's final layer with a linear head and fine-tuning Here, the evaluation itself is framed as a reasoning task. The judge first generates an explicit CoT to explain its rationale before outputting its final judgment.

The primary goal of traditional federated learning is to protect data privacy by enabling distributed edge devices to collaboratively train a shared global model while keeping raw data decentralized at local clients. The rise of large language models (LLMs) has introduced new challenges in distributed systems, as their substantial computational requirements and the need for specialized expertise raise critical concerns about protecting intellectual property (IP). This highlights the need for a federated learning approach that can safeguard both sensitive data and proprietary models. To tackle this challenge, we propose FedQSN, a federated learning approach that leverages random masking to obscure a subnetwork of model parameters and applies quantization to the remaining parameters. Consequently, the server transmits only a privacy-preserving proxy of the global model to clients during each communication round, thus enhancing the model's confidentiality. Experimental results across various models and tasks demonstrate that our approach not only maintains strong model performance in federated learning settings but also achieves enhanced protection of model parameters compared to baseline methods.

Large Language Models (LLMs) often exhibit deficiencies with complex reasoning tasks, such as maths, which we attribute to the discrepancy between human reasoning patterns and those presented in the LLMs' training data. When dealing with complex problems, humans tend to think carefully before expressing solutions. However, they often do not articulate their inner thoughts, including their intentions and chosen methodologies. Consequently, critical insights essential for bridging reasoning steps may be absent in training data collected from human sources. To bridge this gap, we proposes inserting \emph{insight}s between consecutive reasoning steps, which review the status and initiate the next reasoning steps. Unlike prior prompting strategies that rely on a single or a workflow of static prompts to facilitate reasoning, \emph{insight}s are \emph{proactively} generated to guide reasoning processes. We implement our idea as a reasoning framework, named \emph{Thinking Before You Speak} (TBYS), and design a pipeline for automatically collecting and filtering in-context examples for the generation of \emph{insight}s, which alleviates human labeling efforts and fine-tuning overheads. Experiments on challenging mathematical datasets verify the effectiveness of TBYS. Project website: https://gitee.com/jswrt/TBYS

While Large Language Models (LLMs) have emerged as powerful foundational models to solve a variety of tasks, they have also been shown to be prone to hallucinations, i.e., generating responses that sound confident but are actually incorrect or even nonsensical. In this work, we formulate the problem of detecting hallucinations as a hypothesis testing problem and draw parallels to the problem of out-of-distribution detection in machine learning models. We propose a multiple-testing-inspired method to solve the hallucination detection problem, and provide extensive experimental results to validate the robustness of our approach against state-of-the-art methods.

Faithful generation in large language models (LLMs) is challenged by knowledge conflicts between parametric memory and external context. Existing contrastive decoding methods tuned specifically to handle conflict often lack adaptability and can degrade performance in low conflict settings. We introduce CoCoA (Confidence- and Context-Aware Adaptive Decoding), a novel token-level algorithm for principled conflict resolution and enhanced faithfulness. CoCoA resolves conflict by utilizing confidence-aware measures (entropy gap and contextual peakedness) and the generalized divergence between the parametric and contextual distributions. Crucially, CoCoA maintains strong performance even in low conflict settings. Extensive experiments across multiple LLMs on diverse Question Answering (QA), Summarization, and Long-Form Question Answering (LFQA) benchmarks demonstrate CoCoA's state-of-the-art performance over strong baselines like AdaCAD. It yields significant gains in QA accuracy, up to 9.2 points on average compared to the strong baseline AdaCAD, and improves factuality in summarization and LFQA by up to 2.5 points on average across key benchmarks. Additionally, it demonstrates superior sensitivity to conflict variations. CoCoA enables more informed, context-aware, and ultimately more faithful token generation.

Compositional visual reasoning has emerged as a key research frontier in multimodal AI, aiming to endow machines with the human-like ability to decompose visual scenes, ground intermediate concepts, and perform multi-step logical inference. While early surveys focus on monolithic vision-language models or general multimodal reasoning, a dedicated synthesis of the rapidly expanding compositional visual reasoning literature is still missing. We fill this gap with a comprehensive survey spanning 2023 to 2025 that systematically reviews 260+ papers from top venues (CVPR, ICCV, NeurIPS, ICML, ACL, etc.). We first formalize core definitions and describe why compositional approaches offer advantages in cognitive alignment, semantic fidelity, robustness, interpretability, and data efficiency. Next, we trace a five-stage paradigm shift: from prompt-enhanced language-centric pipelines, through tool-enhanced LLMs and tool-enhanced VLMs, to recently minted chain-of-thought reasoning and unified agentic VLMs, highlighting their architectural designs, strengths, and limitations. We then catalog 60+ benchmarks and corresponding metrics that probe compositional visual reasoning along dimensions such as grounding accuracy, chain-of-thought faithfulness, and high-resolution perception. Drawing on these analyses, we distill key insights, identify open challenges (e.g., limitations of LLM-based reasoning, hallucination, a bias toward deductive reasoning, scalable supervision, tool integration, and benchmark limitations), and outline future directions, including world-model integration, human-AI collaborative reasoning, and richer evaluation protocols. By offering a unified taxonomy, historical roadmap, and critical outlook, this survey aims to serve as a foundational reference and inspire the next generation of compositional visual reasoning research.

Large language models (LLMs) and vision-augmented LLMs (VLMs) have significantly advanced medical informatics, diagnostics, and decision support. However, these models exhibit systematic biases, particularly age bias, compromising their reliability and equity. This is evident in their poorer performance on pediatric-focused text and visual question-answering tasks. This bias reflects a broader imbalance in medical research, where pediatric studies receive less funding and representation despite the significant disease burden in children. To address these issues, a new comprehensive multi-modal pediatric question-answering benchmark, PediatricsMQA, has been introduced. It consists of 3,417 text-based multiple-choice questions (MCQs) covering 131 pediatric topics across seven developmental stages (prenatal to adolescent) and 2,067 vision-based MCQs using 634 pediatric images from 67 imaging modalities and 256 anatomical regions. The dataset was developed using a hybrid manual-automatic pipeline, incorporating peer-reviewed pediatric literature, validated question banks, existing benchmarks, and existing QA resources. Evaluating state-of-the-art open models, we find dramatic performance drops in younger cohorts, highlighting the need for age-aware methods to ensure equitable AI support in pediatric care.