Supervised fine-tuning (SFT) with expert demonstrations often suffers from the imitation problem, where models reproduce correct responses without internalizing the underlying reasoning. We propose Critique-Guided Distillation (CGD), a multi-stage training framework that augments SFT with teacher-generated explanatory critiques and refined responses. Instead of directly imitating teacher outputs, a student learns to map the triplet of prompt, its own initial response, and teacher critique into the refined teacher response, thereby capturing both what to output and why. Our analyses show that CGD consistently reduces refinement uncertainty, improves alignment between critiques and responses, and enhances sample efficiency. On reasoning benchmarks, CGD achieves substantial gains across LLaMA and Qwen families, including +15.0% on AMC23 and +12.2% on MATH-500, while avoiding the format drift issues observed in prior critique-based fine-tuning. Importantly, on LLaMA-3.1-8B CGD approaches or exceeds the performance of SimpleRL-Zero, which is a DeepSeek-R1 replication, while requiring 60x less compute. Beyond reasoning, CGD maintains or improves general instruction-following and factual accuracy, matching baseline performance on IFEval, MUSR, TruthfulQA, and BBH. In contrast, prior critique-based methods degrade these capabilities (e.g., -21% on IFEval). Taken together, these results establish CGD} as a robust and generalizable alternative to both conventional SFT and RL-based methods, offering a more efficient path toward advancing the reasoning and safety of large language models.

Large language models (LLMs) excel at generating long-form responses, but evaluating their factuality remains challenging due to complex inter-sentence dependencies within the generated facts. Prior solutions predominantly follow a decompose-decontextualize-verify pipeline but often fail to capture essential context and miss key relational facts. In this paper, we introduce VeriFact, a factuality evaluation framework designed to enhance fact extraction by identifying and resolving incomplete and missing facts to support more accurate verification results. Moreover, we introduce FactRBench , a benchmark that evaluates both precision and recall in long-form model responses, whereas prior work primarily focuses on precision. FactRBench provides reference fact sets from advanced LLMs and human-written answers, enabling recall assessment. Empirical evaluations show that VeriFact significantly enhances fact completeness and preserves complex facts with critical relational information, resulting in more accurate factuality evaluation. Benchmarking various open- and close-weight LLMs on FactRBench indicate that larger models within same model family improve precision and recall, but high precision does not always correlate with high recall, underscoring the importance of comprehensive factuality assessment.

We present OnPrem$.$LLM, a Python-based toolkit for applying large language models (LLMs) to sensitive, non-public data in offline or restricted environments. The system is designed for privacy-preserving use cases and provides prebuilt pipelines for document processing and storage, retrieval-augmented generation (RAG), information extraction, summarization, classification, and prompt/output processing with minimal configuration. OnPrem$.$LLM supports multiple LLM backends -- including llama$.$cpp, Ollama, vLLM, and Hugging Face Transformers -- with quantized model support, GPU acceleration, and seamless backend switching. Although designed for fully local execution, OnPrem$.$LLM also supports integration with a wide range of cloud LLM providers when permitted, enabling hybrid deployments that balance performance with data control. A no-code web interface extends accessibility to non-technical users.

Integrating large language models (LLMs) as priors in reinforcement learning (RL) offers significant advantages but comes with substantial computational costs. We present a principled cache-efficient framework for posterior sampling with LLM-derived priors that dramatically reduces these costs while maintaining high performance. At the core of our approach is an adaptive caching mechanism, where cache parameters are meta-optimized using surrogate gradients derived from policy performance. This design enables efficient inference across both discrete text environments (e.g., TextWorld, ALFWorld) and continuous control domains (e.g., MuJoCo), achieving a 3.8--4.7$\times$ reduction in LLM queries and 4.0--12.0$\times$ lower median latencies (85--93\,ms on a consumer GPU) while retaining 96--98\% of uncached performance. Our theoretical analysis provides KL divergence bounds on approximation quality, validated empirically. The framework extends to offline RL, where our CQL-Prior variant improves performance by 14--29\% and reduces training time by 38--40\%. Extensive evaluations across a diverse suite of eight tasks demonstrate the generalizability and practical viability of LLM-guided RL in resource-constrained settings.

Large Language Models (LLMs) excel at many tasks, yet they struggle to produce truly creative, diverse ideas. In this paper, we introduce a novel approach that enhances LLM creativity. We apply LLMs for translating between natural language and structured representations, and perform the core creative leap via cognitively inspired manipulations on these representations. Our notion of creativity goes beyond superficial token-level variations; rather, we recombine structured representations of existing ideas, enabling our system to effectively explore a more abstract landscape of ideas. We demonstrate our approach in the culinary domain with DishCOVER, a model that generates creative recipes. Experiments and domain-expert evaluations reveal that our outputs, which are mostly coherent and feasible, significantly surpass GPT-4o in terms of novelty and diversity, thus outperforming it in creative generation. We hope our work inspires further research into structured creativity in AI.

Recent advances in large reasoning language models (LRLMs) rely on test-time scaling, which extends long chain-of-thought (CoT) generation to solve complex tasks. However, overthinking in long CoT not only slows down the efficiency of problem solving, but also risks accuracy loss due to the extremely detailed or redundant reasoning steps. We propose a simple yet effective method that allows LLMs to self-truncate CoT sequences by early exit during generation. Instead of relying on fixed heuristics, the proposed method monitors model behavior at potential reasoning transition points and dynamically terminates the next reasoning chain's generation when the model exhibits high confidence in a trial answer. Our method requires no additional training and can be seamlessly integrated into existing o1-like reasoning LLMs. Experiments on 10 reasoning benchmarks (e.g., GSM8K, MATH-500, AMC, GPQA, AIME and LiveCodeBench) show that the proposed method is consistently effective on 11 cutting-edge reasoning LLMs of varying series and sizes, reducing the length of CoT sequences by an average of 19.1% to 80.1% while improving accuracy by 0.3% to 5.0%.

This study investigates the relationship between deep learning (DL) model accuracy and expert agreement in classifying crash narratives. We evaluate five DL models -- including BERT variants, USE, and a zero-shot classifier -- against expert labels and narratives, and extend the analysis to four large language models (LLMs): GPT-4, LLaMA 3, Qwen, and Claude. Our findings reveal an inverse relationship: models with higher technical accuracy often show lower agreement with human experts, while LLMs demonstrate stronger expert alignment despite lower accuracy. We use Cohen's Kappa and Principal Component Analysis (PCA) to quantify and visualize model-expert agreement, and employ SHAP analysis to explain misclassifications. Results show that expert-aligned models rely more on contextual and temporal cues than location-specific keywords. These findings suggest that accuracy alone is insufficient for safety-critical NLP tasks. We argue for incorporating expert agreement into model evaluation frameworks and highlight the potential of LLMs as interpretable tools in crash analysis pipelines.

Large language models (LLMs) are increasingly applied to multi-modal data analysis--not necessarily because they offer the most precise answers, but because they provide fluent, flexible interfaces for interpreting complex inputs. Y et this fluency often conceals a deeper structural failure: the prevailing "Prompt-to-Answer" paradigm treats LLMs as black-box analysts, collapsing evidence, reasoning, and conclusions into a single, opaque response. The result is brittle, unverifiable, and frequently misleading. We argue for a fundamental shift: from generation to structured extraction, from monolithic prompts to modular, agent-based workflows. LLMs should not serve as oracles, but as collaborators--specialized in tasks like extraction, translation, and linkage--embedded within transparent workflows that enable step-by-step reasoning and verification. We propose Data-Puzzle, a conceptual multi-agent framework that decomposes complex questions, structures information into interpretable forms (e.g., tables, graphs), and coordinates agent roles to support transparent and verifiable analysis. This framework serves as an aspirational blueprint for restoring visibility and control in LLMdriven analytics--transforming opaque answers into traceable processes, and brittle fluency into accountable insight. This is not a marginal refinement; it is a call to reimagine how we build trustworthy, auditable analytic systems in the era of large language models. Structure is not a constraint--it is the path to clarity.

Optimal hyperparameter selection is critical for maximizing the performance of neural networks in computer vision, particularly as architectures become more complex. This work explores the use of large language models (LLMs) for hyperparameter optimization by fine-tuning a parameter-efficient version of Code Llama using LoRA. The resulting model produces accurate and computationally efficient hyperparameter recommendations across a wide range of vision architectures. Unlike traditional methods such as Optuna, which rely on resource-intensive trial-and-error procedures, our approach achieves competitive or superior Root Mean Square Error (RMSE) while substantially reducing computational overhead. Importantly, the models evaluated span image-centric tasks such as classification, detection, and segmentation, fundamental components in many image manipulation pipelines including enhancement, restoration, and style transfer . Our results demonstrate that LLM-based optimization not only rivals established Bayesian methods like Tree-structured Parzen Estimators (TPE), but also accelerates tuning for real-world applications requiring perceptual quality and low-latency processing.

Compositionality, or correctly recognizing scenes as compositions of atomic visual concepts, remains difficult for multimodal large language models (MLLMs). Even state of the art MLLMs such as GPT-4o can make mistakes in distinguishing compositions like "dog chasing cat" vs "cat chasing dog". While on Winoground, a benchmark for measuring such reasoning, MLLMs have made significant progress, they are still far from a human's performance. W e show that compositional reasoning in these models can be improved by elucidating such concepts via data, where a model is trained to prefer the correct caption for an image over a close but incorrect one. W e introduce SCRAMBLe: Synthetic Compositional Reasoning Augmentation of MLLMs with Binary preference Learning, an approach for preference tuning open-weight MLLMs on synthetic preference data generated in a fully automated manner from existing image-caption data. SCRAMBLe holistically improves these MLLMs' compositional reasoning capabilities which we can see through significant improvements across multiple vision language composition-ality benchmarks, as well as smaller but significant improvements on general question answering tasks. As a sneak peek, SCRAMBLe tuned Molmo-7B model improves on Winoground from 49.5% to 54.8% (best reported to date), while improving by 1% on more general visual question answering tasks.