In this paper, we argue that current safety alignment research efforts for large language models are hindered by many intertwined sources of noise, such as small datasets, methodological inconsistencies, and unreliable evaluation setups. This can, at times, make it impossible to evaluate and compare attacks and defenses fairly, thereby slowing progress. We systematically analyze the LLM safety evaluation pipeline, covering dataset curation, optimization strategies for automated red-teaming, response generation, and response evaluation using LLM judges. At each stage, we identify key issues and highlight their practical impact. We also propose a set of guidelines for reducing noise and bias in evaluations of future attack and defense papers. Lastly, we offer an opposing perspective, highlighting practical reasons for existing limitations. We believe that addressing the outlined problems in future research will improve the field's ability to generate easily comparable results and make measurable progress.

The use of large language model (LLM)-powered chatbots, such as ChatGPT, has become popular across various domains, supporting a range of tasks and processes. However, due to the intrinsic complexity of LLMs, effective prompting is more challenging than it may seem. This highlights the need for innovative educational and support strategies that are both widely accessible and seamlessly integrated into task workflows. Yet, LLM prompting is highly task- and domain-dependent, limiting the effectiveness of generic approaches. In this study, we explore whether LLM-based methods can facilitate learning assessments by using ad-hoc guidelines and a minimal number of annotated prompt samples. Our framework transforms these guidelines into features that can be identified within learners' prompts. Using these feature descriptions and annotated examples, we create few-shot learning detectors. We then evaluate different configurations of these detectors, testing three state-of-the-art LLMs and ensembles. We run experiments with cross-validation on a sample of original prompts, as well as tests on prompts collected from task-naive learners. Our results show how LLMs perform on feature detection. Notably, GPT- 4 demonstrates strong performance on most features, while closely related models, such as GPT-3 and GPT-3.5 Turbo (Instruct), show inconsistent behaviors in feature classification. These differences highlight the need for further research into how design choices impact feature selection and prompt detection. Our findings contribute to the fields of generative AI literacy and computer-supported learning assessment, offering valuable insights for both researchers and practitioners.

Long-context modeling has drawn more and more attention in the area of Large Language Models (LLMs). Continual training with long-context data becomes the de-facto method to equip LLMs with the ability to process long inputs. However, it still remains an open challenge to measure the quality of long-context training data. To address this issue, we propose a Long-context data selection framework with Attention-based Dependency Measurement (LADM), which can efficiently identify high-quality long-context data from a large-scale, multi-domain pre-training corpus. LADM leverages the retrieval capabilities of the attention mechanism to capture contextual dependencies, ensuring a comprehensive quality measurement of long-context data. Experimental results show that our LADM framework significantly boosts the performance of LLMs on multiple long-context tasks with only 1B tokens for continual training.

Large Language Models (LLMs) offer remarkable capabilities in code generation, natural language processing, and domain-specific reasoning. Their potential in aiding quantum software development remains underexplored, particularly for the PennyLane framework-a leading platform for hybrid quantum-classical computing. To address this gap, we introduce a novel, high-quality dataset comprising 3,347 PennyLane-specific code samples of quantum circuits and their contextual descriptions, specifically curated to train/fine-tune LLM-based quantum code assistance. Our key contributions are threefold: (1) the automatic creation and open-source release of a comprehensive PennyLane dataset leveraging quantum computing textbooks, official documentation, and open-source repositories; (2) the development of a systematic methodology for data refinement, annotation, and formatting to optimize LLM training efficiency; and (3) a thorough evaluation, based on a Retrieval-Augmented Generation (RAG) framework, demonstrating the effectiveness of our dataset in streamlining PennyLane code generation and improving quantum development workflows. Compared to existing efforts that predominantly focus on Qiskit, our dataset significantly broadens the spectrum of quantum frameworks covered in AI-driven code assistance. By bridging this gap and providing reproducible dataset-creation methodologies, we aim to advance the field of AI-assisted quantum programming, making quantum computing more accessible to both newcomers and experienced developers.

Abstract--Emergency search and rescue (SAR) operations often require rapid and precise target identification in complex environments where traditional manual drone control is inefficient. This system consists of two aspects: 1) A multimodal system which harnesses the power of Visual Language Model (VLM) and the natural language processing capabilities of ChatGPT-4o (LLM) for scene interpretation. This work aims at improving response times in emergency SAR operations by providing a more intuitive and natural approach to the operator to plan the SAR mission while allowing the drone to carry out that mission in a rapid and safe manner. When tested, our approach was faster on an average by 33.75% when compared with an off-the-shelf autopilot and 54.6% when compared with a human pilot. Search and rescue (SAR) operations in disaster-stricken and hazardous environments require fast and efficient situational assessment to locate survivors and critical infrastructure.

Very large language models (LLMs) such as GPT-4 have shown the ability to handle complex tasks by generating and self-refining step-by-step rationales. Smaller language models (SLMs), typically with < 13B parameters, have been improved by using the data generated from very-large LMs through knowledge distillation. Limited success has been achieved at improving the ability of an SLM to explore the space of possible rationales and evaluate them by itself through self-deliberation. To address this, we propose COALITION, a trainable framework that facilitates interaction between two variants of the same SLM and trains them to generate and refine rationales optimized for the end-task. The variants exhibit different behaviors to produce a set of diverse candidate rationales during the generation and refinement steps. The model is then trained via Selective Rationale Optimization (SRO) to prefer generating rationale candidates that maximize the likelihood of producing the ground-truth answer. During inference, COALITION employs a controller to select the suitable variant for generating and refining the rationales. On five different datasets covering mathematical problems, commonsense reasoning, and natural language inference, COALITION outperforms several baselines by up to 5%. Our ablation studies reveal that cross-communication between the two variants performs better than using the single model to self-refine the rationales. We also demonstrate the applicability of COALITION for LMs of varying scales (4B to 14B parameters) and model families (Mistral, Llama, Qwen, Phi). We release the code for this work here. Modern large language models (LLMs) with hundreds of billions of parameters, such as GPT-4 (Achiam et al., 2023) and PaLM-540B (Chowdhery et al., 2022) have shown a remarkable ability to solve complex tasks by generating step-by-step rationales (Wei et al., 2022a;b; Kojima et al., 2022) and refining them through self-correction (Wang et al., 2023b; Welleck et al., 2023). The ability to think step-by-step becomes more prominent with scale, while smaller language models (SLMs), typically 13B, struggle to generate good quality rationales (Valmeekam et al., 2022; Weng et al., 2023). However, owing to the advantages of SLMs such as lesser costs, latency, and compute requirements, significant efforts have been made to improve their ability to handle complex tasks by using feedback obtained through interactions with LLMs (Tunstall et al., 2023; Hsieh et al., 2023; Gou et al., 2024; Wang et al., 2024b). For instance, OpenAI's usage terms prohibit using GPT-generated outputs to train other models for commercial use. Consequently, efforts have been made to improve SLM performance without reliance on an external teacher LLM. The sample is fed to a controller (step 1) to select the variant (steps 2-3) that generates a rationale (step 4).

This paper investigates the challenges of affect control in large language models (LLMs), focusing on their ability to express appropriate emotional states during extended dialogues. We evaluated state-of-the-art open-weight LLMs to assess their affective expressive range in terms of arousal and valence. Our study employs a novel methodology combining LLM-based sentiment analysis with multiturn dialogue simulations between LLMs. We quantify the models' capacity to express a wide spectrum of emotions and how they fluctuate during interactions. Our findings reveal significant variations among LLMs in their ability to maintain consistent affect, with some models demonstrating more stable emotional trajectories than others. Furthermore, we identify key challenges in affect control, including difficulties in producing and maintaining extreme emotional states and limitations in adapting affect to changing conversational contexts. These findings have important implications for the development of more emotionally intelligent AI systems and highlight the need for improved affect modelling in LLMs.

The UAV-VLPA* (Visual-Language-Planning-and-Action) system represents a cutting-edge advancement in aerial robotics, designed to enhance communication and operational efficiency for unmanned aerial vehicles (UAVs). By integrating advanced planning capabilities, the system addresses the Traveling Salesman Problem (TSP) to optimize flight paths, reducing the total trajectory length by 18.5\% compared to traditional methods. Additionally, the incorporation of the A* algorithm enables robust obstacle avoidance, ensuring safe and efficient navigation in complex environments. The system leverages satellite imagery processing combined with the Visual Language Model (VLM) and GPT's natural language processing capabilities, allowing users to generate detailed flight plans through simple text commands. This seamless fusion of visual and linguistic analysis empowers precise decision-making and mission planning, making UAV-VLPA* a transformative tool for modern aerial operations. With its unmatched operational efficiency, navigational safety, and user-friendly functionality, UAV-VLPA* sets a new standard in autonomous aerial robotics, paving the way for future innovations in the field.

Generative models have recently gained attention in recommendation systems by directly predicting item identifiers from user interaction sequences. However, existing methods suffer from significant information loss due to the separation of stages such as quantization and sequence modeling, hindering their ability to achieve the modeling precision and accuracy of sequential dense retrieval techniques. Integrating generative and dense retrieval methods remains a critical challenge. To address this, we introduce the Cascaded Organized Bi-Represented generAtive retrieval (COBRA) framework, which innovatively integrates sparse semantic IDs and dense vectors through a cascading process. Our method alternates between generating these representations by first generating sparse IDs, which serve as conditions to aid in the generation of dense vectors. End-to-end training enables dynamic refinement of dense representations, capturing both semantic insights and collaborative signals from user-item interactions. During inference, COBRA employs a coarse-to-fine strategy, starting with sparse ID generation and refining them into dense vectors via the generative model. We further propose BeamFusion, an innovative approach combining beam search with nearest neighbor scores to enhance inference flexibility and recommendation diversity. Extensive experiments on public datasets and offline tests validate our method's robustness. Online A/B tests on a real-world advertising platform with over 200 million daily users demonstrate substantial improvements in key metrics, highlighting COBRA's practical advantages.

Personalizing Large Language Models (LLMs) has become a critical step in facilitating their widespread application to enhance individual life experiences. In pursuit of personalization, distilling key preference information from an individual's historical data as instructional preference context to customize LLM generation has emerged as a promising direction. However, these methods face a fundamental limitation by overlooking the inter-user comparative analysis, which is essential for identifying the inter-user differences that truly shape preferences. To address this limitation, we propose Difference-aware Personalization Learning (DPL), a novel approach that emphasizes extracting inter-user differences to enhance LLM personalization. DPL strategically selects representative users for comparison and establishes a structured standard to extract meaningful, task-relevant differences for customizing LLM generation. Extensive experiments on real-world datasets demonstrate that DPL significantly enhances LLM personalization. We release our code at https://github.com/SnowCharmQ/DPL.