Functional fixedness, a cognitive bias that restricts users' interactions with a new system or tool to expected or familiar ways, limits the full potential of Large Language Model (LLM)-enabled chat search, especially in complex and exploratory tasks. To investigate its impact, we conducted a crowdsourcing study with 450 participants, each completing one of six decision-making tasks spanning public safety, diet and health management, sustainability, and AI ethics. Participants engaged in a multi-prompt conversation with ChatGPT to address the task, allowing us to compare pre-chat intent-based expectations with observed interactions. We found that: 1) Several aspects of pre-chat expectations are closely associated with users' prior experiences with ChatGPT, search engines, and virtual assistants; 2) Prior system experience shapes language use and prompting behavior. Frequent ChatGPT users reduced deictic terms and hedge words and frequently adjusted prompts. Users with rich search experience maintained structured, less-conversational queries with minimal modifications. Users of virtual assistants favored directive, command-like prompts, reinforcing functional fixedness; 3) When the system failed to meet expectations, participants generated more detailed prompts with increased linguistic diversity, reflecting adaptive shifts. These findings suggest that while preconceived expectations constrain early interactions, unmet expectations can motivate behavioral adaptation. With appropriate system support, this may promote broader exploration of LLM capabilities. This work also introduces a typology for user intents in chat search and highlights the importance of mitigating functional fixedness to support more creative and analytical use of LLMs.
This survey investigates foundational technologies essential for developing effective Large Language Model (LLM)-based multi-agent systems. Aiming to answer how best to optimize these systems for collaborative, dynamic environments, we focus on four critical areas: Architecture, Memory, Planning, and Technologies/Frameworks. By analyzing recent advancements and their limitations - such as scalability, real-time response challenges, and agent coordination constraints, we provide a detailed view of the technological landscape. Frameworks like the Mixture of Agents architecture and the ReAct planning model exemplify current innovations, showcasing improvements in role assignment and decision-making. This review synthesizes key strengths and persistent challenges, offering practical recommendations to enhance system scalability, agent collaboration, and adaptability. Our findings provide a roadmap for future research, supporting the creation of robust, efficient multi-agent systems that advance both individual agent performance and collective system resilience.
Pretraining data curation is a cornerstone in Large Language Model (LLM) development, leading to growing research on quality filtering of large web corpora. From statistical quality flags to LLM-based labeling systems, datasets are divided into categories, frequently reducing to a binary: those passing the filters deemed as valuable examples, others discarded as useless or detrimental. However, a more detailed understanding of the contribution of different kinds of texts to model performance is still largely lacking. In this article, we present the first study utilizing registers (also known as genres) - a widely used standard in corpus linguistics to model linguistic variation - to curate pretraining datasets and investigate the effect of register on the performance of LLMs. We perform comparative studies by training models with register classified data and evaluating them using standard benchmarks, and show that the register of pretraining data substantially affects model performance. We uncover surprising relationships between the pretraining material and the resulting models: using the News register results in subpar performance, and on the contrary, including the Opinion class, covering texts such as reviews and opinion blogs, is highly beneficial. While a model trained on the entire unfiltered dataset outperforms those trained on datasets limited to a single register, combining well-performing registers like How-to-Instructions, Informational Description, and Opinion leads to major improvements. Furthermore, analysis of individual benchmark results reveals key differences in the strengths and drawbacks of specific register classes as pretraining data. These findings show that register is an important explainer of model variation and can facilitate more deliberate future data selection practices.
Predicting future events stands as one of the ultimate aspirations of artificial intelligence. Recent advances in large language model (LLM)-based systems have shown remarkable potential in forecasting future events, thereby garnering significant interest in the research community. Currently, several benchmarks have been established to evaluate the forecasting capabilities by formalizing the event prediction as a retrieval-augmented generation (RAG) and reasoning task. In these benchmarks, each prediction question is answered with relevant retrieved news articles. However, because there is no consideration on whether the questions can be supported by valid or sufficient supporting rationales, some of the questions in these benchmarks may be inherently noninferable. To address this issue, we introduce a new benchmark, PROPHET, which comprises inferable forecasting questions paired with relevant news for retrieval. To ensure the inferability of the benchmark, we propose Causal Intervened Likelihood (CIL), a statistical measure that assesses inferability through causal inference. In constructing this benchmark, we first collected recent trend forecasting questions and then filtered the data using CIL, resulting in an inferable benchmark for event prediction. Through extensive experiments, we first demonstrate the validity of CIL and in-depth investigations into event prediction with the aid of CIL. Subsequently, we evaluate several representative prediction systems on PROPHET, drawing valuable insights for future directions.
The reproduction of state-of-the-art multimodal LLM pre-training faces barriers at every stage of the pipeline, including high-quality data filtering, multimodal data mixture strategies, sequence packing techniques, and training frameworks. We introduce Open-Qwen2VL, a fully open-source 2B-parameter Multimodal Large Language Model pre-trained efficiently on 29M image-text pairs using only 220 A100-40G GPU hours. Our approach employs low-to-high dynamic image resolution and multimodal sequence packing to significantly enhance pre-training efficiency. The training dataset was carefully curated using both MLLM-based filtering techniques (e.g., MLM-Filter) and conventional CLIP-based filtering methods, substantially improving data quality and training efficiency. The Open-Qwen2VL pre-training is conducted on academic level 8xA100-40G GPUs at UCSB on 5B packed multimodal tokens, which is 0.36% of 1.4T multimodal pre-training tokens of Qwen2-VL. The final instruction-tuned Open-Qwen2VL outperforms partially-open state-of-the-art MLLM Qwen2-VL-2B on various multimodal benchmarks of MMBench, SEEDBench, MMstar, and MathVista, indicating the remarkable training efficiency of Open-Qwen2VL. We open-source all aspects of our work, including compute-efficient and data-efficient training details, data filtering methods, sequence packing scripts, pre-training data in WebDataset format, FSDP-based training codebase, and both base and instruction-tuned model checkpoints. We redefine "fully open" for multimodal LLMs as the complete release of: 1) the training codebase, 2) detailed data filtering techniques, and 3) all pre-training and supervised fine-tuning data used to develop the model.
Referring video object segmentation (RVOS) is a challenging task that requires the model to segment the object in a video given the language description. MeViS is a recently proposed dataset that contains motion expressions of the target objects, leading to a challenging benchmark, compared with existing RVOS benchmarks. On the other hand, for referring expression tasks, a new trend is to adopt multi-modal large language model (MLLM) to achieve better image and text alignment. In this report, we show that with a simple modification to the test time inference method on stronger MLLMs, we can lead to stronger results on MeVIS. In particular, we adopt the recent method Sa2VA, a unified model for dense grounded understanding of both images and videos. By enlarging the scope of key frames, without any further training, we can achieve the 3rd place in the 4th PVUW workshop.
LLM-as-a-Judge is a framework that uses an LLM (large language model) to evaluate the quality of natural language text - typically text that is also generated by an LLM. This framework holds great promise due to its relative low-cost, ease of use, and strong correlations with human stylistic preferences. However, LLM Judges have been shown to exhibit biases that can distort their judgments. We evaluate how well LLM Judges can grade whether a given response to a conversational question is correct, an ability crucial to soundly estimating the overall response quality. To do so, we create and publicly release a human-annotated dataset with labels of correctness for 1,200 LLM responses. We source questions from a combination of existing datasets and a novel, challenging benchmark (BFF-Bench) created for this analysis. We demonstrate a strong connection between an LLM's ability to correctly answer a question and grade responses to that question. Although aggregate level statistics might imply a judge has high agreement with human annotators, it will struggle on the subset of questions it could not answer. To address this issue, we recommend a simple solution: provide the judge with a correct, human-written reference answer. We perform an in-depth analysis on how reference quality can affect the performance of an LLM Judge. We show that providing a weaker judge (e.g. Qwen 2.5 7B) with higher quality references reaches better agreement with human annotators than a stronger judge (e.g. GPT-4o) with synthetic references.
Referring expression segmentation (RES) aims at segmenting the entities' masks that match the descriptive language expression. While traditional RES methods primarily address object-level grounding, real-world scenarios demand a more versatile framework that can handle multiple levels of target granularity, such as multi-object, single object or part-level references. This introduces great challenges due to the diverse and nuanced ways users describe targets. However, existing datasets and models mainly focus on designing grounding specialists for object-level target localization, lacking the necessary data resources and unified frameworks for the more practical multi-grained RES. In this paper, we take a step further towards visual granularity unified RES task. To overcome the limitation of data scarcity, we introduce a new multi-granularity referring expression segmentation (MRES) task, alongside the RefCOCOm benchmark, which includes part-level annotations for advancing finer-grained visual understanding. In addition, we create MRES-32M, the largest visual grounding dataset, comprising over 32.2M masks and captions across 1M images, specifically designed for part-level vision-language grounding. To tackle the challenges of multi-granularity RES, we propose UniRES++, a unified multimodal large language model that integrates object-level and part-level RES tasks. UniRES++ incorporates targeted designs for fine-grained visual feature exploration. With the joint model architecture and parameters, UniRES++ achieves state-of-the-art performance across multiple benchmarks, including RefCOCOm for MRES, gRefCOCO for generalized RES, and RefCOCO, RefCOCO+, RefCOCOg for classic RES. To foster future research into multi-grained visual grounding, our RefCOCOm benchmark, MRES-32M dataset and model UniRES++ will be publicly available at https://github.com/Rubics-Xuan/MRES.
Vector Pseudo Relevance Feedback (VPRF) has shown promising results in improving BERT-based dense retrieval systems through iterative refinement of query representations. This paper investigates the generalizability of VPRF to Large Language Model (LLM) based dense retrievers. We introduce LLM-VPRF and evaluate its effectiveness across multiple benchmark datasets, analyzing how different LLMs impact the feedback mechanism. Our results demonstrate that VPRF's benefits successfully extend to LLM architectures, establishing it as a robust technique for enhancing dense retrieval performance regardless of the underlying models. This work bridges the gap between VPRF with traditional BERT-based dense retrievers and modern LLMs, while providing insights into their future directions.
Post-Traumatic Stress Disorder (PTSD) remains underdiagnosed in clinical settings, presenting opportunities for automated detection to identify patients. This study evaluates natural language processing approaches for detecting PTSD from clinical interview transcripts. We compared general and mental health-specific transformer models (BERT/RoBERTa), embedding-based methods (SentenceBERT/LLaMA), and large language model prompting strategies (zero-shot/few-shot/chain-of-thought) using the DAIC-WOZ dataset. Domain-specific models significantly outperformed general models (Mental-RoBERTa F1=0.643 vs. RoBERTa-base 0.485). LLaMA embeddings with neural networks achieved the highest performance (F1=0.700). Zero-shot prompting using DSM-5 criteria yielded competitive results without training data (F1=0.657). Performance varied significantly across symptom severity and comorbidity status, with higher accuracy for severe PTSD cases and patients with comorbid depression. Our findings highlight the potential of domain-adapted embeddings and LLMs for scalable screening while underscoring the need for improved detection of nuanced presentations and offering insights for developing clinically viable AI tools for PTSD assessment.
The increasing global prevalence of mental disorders, such as depression and PTSD, requires objective and scalable diagnostic tools. Traditional clinical assessments often face limitations in accessibility, objectivity, and consistency. This paper investigates the potential of multimodal machine learning to address these challenges, leveraging the complementary information available in text, audio, and video data. Our approach involves a comprehensive analysis of various data preprocessing techniques, including novel chunking and utterance-based formatting strategies. We systematically evaluate a range of state-of-the-art embedding models for each modality and employ Convolutional Neural Networks (CNNs) and Bidirectional LSTM Networks (BiLSTMs) for feature extraction. We explore data-level, feature-level, and decision-level fusion techniques, including a novel integration of Large Language Model (LLM) predictions. We also investigate the impact of replacing Multilayer Perceptron classifiers with Support Vector Machines. We extend our analysis to severity prediction using PHQ-8 and PCL-C scores and multi-class classification (considering co-occurring conditions). Our results demonstrate that utterance-based chunking significantly improves performance, particularly for text and audio modalities. Decision-level fusion, incorporating LLM predictions, achieves the highest accuracy, with a balanced accuracy of 94.8% for depression and 96.2% for PTSD detection. The combination of CNN-BiLSTM architectures with utterance-level chunking, coupled with the integration of external LLM, provides a powerful and nuanced approach to the detection and assessment of mental health conditions. Our findings highlight the potential of MMML for developing more accurate, accessible, and personalized mental healthcare tools.
Atomicity violations in interrupt-driven programs pose a significant threat to software safety in critical systems. These violations occur when the execution sequence of operations on shared resources is disrupted by asynchronous interrupts. Detecting atomicity violations is challenging due to the vast program state space, application-level code dependencies, and complex domain-specific knowledge. We propose Clover, a hybrid framework that integrates static analysis with large language model (LLM) agents to detect atomicity violations in real-world programs. Clover first performs static analysis to extract critical code snippets and operation information. It then initiates a multi-agent process, where the expert agent leverages domain-specific knowledge to detect atomicity violations, which are subsequently validated by the judge agent. Evaluations on RaceBench 2.1, SV-COMP, and RWIP demonstrate that Clover achieves a precision/recall of 92.3%/86.6%, outperforming existing approaches by 27.4-118.2% on F1-score.
Over the past two decades, researchers have made significant advancements in simulating human crowds, yet these efforts largely focus on low-level tasks like collision avoidance and a narrow range of behaviors such as path following and flocking. However, creating compelling crowd scenes demands more than just functional movement-it requires capturing high-level interactions between agents, their environment, and each other over time. To address this issue, we introduce Gen-C, a generative model to automate the task of authoring high-level crowd behaviors. Gen-C bypasses the labor-intensive and challenging task of collecting and annotating real crowd video data by leveraging a large language model (LLM) to generate a limited set of crowd scenarios, which are subsequently expanded and generalized through simulations to construct time-expanded graphs that model the actions and interactions of virtual agents. Our method employs two Variational Graph Auto-Encoders guided by a condition prior network: one dedicated to learning a latent space for graph structures (agent interactions) and the other for node features (agent actions and navigation). This setup enables the flexible generation of dynamic crowd interactions. The trained model can be conditioned on natural language, empowering users to synthesize novel crowd behaviors from text descriptions. We demonstrate the effectiveness of our approach in two scenarios, a University Campus and a Train Station, showcasing its potential for populating diverse virtual environments with agents exhibiting varied and dynamic behaviors that reflect complex interactions and high-level decision-making patterns.
Planning methods with high adaptability to dynamic environments are crucial for the development of autonomous and versatile robots. We propose a method for leveraging a large language model (GPT-4o) to automatically generate networks capable of adapting to dynamic environments. The proposed method collects environmental "status," representing conditions and goals, and uses them to generate agents. These agents are interconnected on the basis of specific conditions, resulting in networks that combine flexibility and generality. We conducted evaluation experiments to compare the networks automatically generated with the proposed method with manually constructed ones, confirming the comprehensiveness of the proposed method's networks and their higher generality. This research marks a significant advancement toward the development of versatile planning methods applicable to robotics, autonomous vehicles, smart systems, and other complex environments.
Finding deletion-correcting codes of maximum size has been an open problem for over 70 years, even for a single deletion. In this paper, we propose a novel approach for constructing deletion-correcting codes. A code is a set of sequences satisfying certain constraints, and we construct it by greedily adding the highest-priority sequence according to a priority function. To find good priority functions, we leverage FunSearch, a large language model (LLM)-guided evolutionary search proposed by Romera et al., 2024. FunSearch iteratively generates, evaluates, and refines priority functions to construct large deletion-correcting codes. For a single deletion, our evolutionary search finds functions that construct codes which match known maximum sizes, reach the size of the largest (conjectured optimal) Varshamov-Tenengolts codes where the maximum is unknown, and independently rediscover them in equivalent form. For two deletions, we find functions that construct codes with new best-known sizes for code lengths \( n = 12, 13 \), and \( 16 \), establishing improved lower bounds. These results demonstrate the potential of LLM-guided search for information theory and code design and represent the first application of such methods for constructing error-correcting codes.
Most discussions about Large Language Model (LLM) safety have focused on single-agent settings but multi-agent LLM systems now create novel adversarial risks because their behavior depends on communication between agents and decentralized reasoning. In this work, we innovatively focus on attacking pragmatic systems that have constrains such as limited token bandwidth, latency between message delivery, and defense mechanisms. We design a $\textit{permutation-invariant adversarial attack}$ that optimizes prompt distribution across latency and bandwidth-constraint network topologies to bypass distributed safety mechanisms within the system. Formulating the attack path as a problem of $\textit{maximum-flow minimum-cost}$, coupled with the novel $\textit{Permutation-Invariant Evasion Loss (PIEL)}$, we leverage graph-based optimization to maximize attack success rate while minimizing detection risk. Evaluating across models including $\texttt{Llama}$, $\texttt{Mistral}$, $\texttt{Gemma}$, $\texttt{DeepSeek}$ and other variants on various datasets like $\texttt{JailBreakBench}$ and $\texttt{AdversarialBench}$, our method outperforms conventional attacks by up to $7\times$, exposing critical vulnerabilities in multi-agent systems. Moreover, we demonstrate that existing defenses, including variants of $\texttt{Llama-Guard}$ and $\texttt{PromptGuard}$, fail to prohibit our attack, emphasizing the urgent need for multi-agent specific safety mechanisms.
Artificial intelligence chatbots driven by large language models (LLMs) have the potential to increase public science literacy and support scientific research, as they can quickly summarize complex scientific information in accessible terms. However, when summarizing scientific texts, LLMs may omit details that limit the scope of research conclusions, leading to generalizations of results broader than warranted by the original study. We tested 10 prominent LLMs, including ChatGPT-4o, ChatGPT-4.5, DeepSeek, LLaMA 3.3 70B, and Claude 3.7 Sonnet, comparing 4900 LLM-generated summaries to their original scientific texts. Even when explicitly prompted for accuracy, most LLMs produced broader generalizations of scientific results than those in the original texts, with DeepSeek, ChatGPT-4o, and LLaMA 3.3 70B overgeneralizing in 26 to 73% of cases. In a direct comparison of LLM-generated and human-authored science summaries, LLM summaries were nearly five times more likely to contain broad generalizations (OR = 4.85, 95% CI [3.06, 7.70]). Notably, newer models tended to perform worse in generalization accuracy than earlier ones. Our results indicate a strong bias in many widely used LLMs towards overgeneralizing scientific conclusions, posing a significant risk of large-scale misinterpretations of research findings. We highlight potential mitigation strategies, including lowering LLM temperature settings and benchmarking LLMs for generalization accuracy.
Large Language Models (LLMs) have emerged as powerful tools, but their inherent safety risks - ranging from harmful content generation to broader societal harms - pose significant challenges. These risks can be amplified by the recent adversarial attacks, fine-tuning vulnerabilities, and the increasing deployment of LLMs in high-stakes environments. Existing safety-enhancing techniques, such as fine-tuning with human feedback or adversarial training, are still vulnerable as they address specific threats and often fail to generalize across unseen attacks, or require manual system-level defenses. This paper introduces RepBend, a novel approach that fundamentally disrupts the representations underlying harmful behaviors in LLMs, offering a scalable solution to enhance (potentially inherent) safety. RepBend brings the idea of activation steering - simple vector arithmetic for steering model's behavior during inference - to loss-based fine-tuning. Through extensive evaluation, RepBend achieves state-of-the-art performance, outperforming prior methods such as Circuit Breaker, RMU, and NPO, with up to 95% reduction in attack success rates across diverse jailbreak benchmarks, all with negligible reduction in model usability and general capabilities.
Dialect translation plays a key role in enabling seamless interaction across heterogeneous database systems. However, translating SQL queries between different dialects (e.g., from PostgreSQL to MySQL) remains a challenging task due to syntactic discrepancies and subtle semantic variations. Existing approaches including manual rewriting, rule-based systems, and large language model (LLM)-based techniques often involve high maintenance effort (e.g., crafting custom translation rules) or produce unreliable results (e.g., LLM generates non-existent functions), especially when handling complex queries. In this demonstration, we present CrackSQL, the first hybrid SQL dialect translation system that combines rule and LLM-based methods to overcome these limitations. CrackSQL leverages the adaptability of LLMs to minimize manual intervention, while enhancing translation accuracy by segmenting lengthy complex SQL via functionality-based query processing. To further improve robustness, it incorporates a novel cross-dialect syntax embedding model for precise syntax alignment, as well as an adaptive local-to-global translation strategy that effectively resolves interdependent query operations. CrackSQL supports three translation modes and offers multiple deployment and access options including a web console interface, a PyPI package, and a command-line prompt, facilitating adoption across a variety of real-world use cases
This study presents an empirical case study to assess the efficacy and reliability of DeepSeek-V3, an emerging large language model, within the context of computer education. The evaluation employs both CCNA simulation questions and real-world inquiries concerning computer network security posed by Chinese network engineers. To ensure a thorough evaluation, diverse dimensions are considered, encompassing role dependency, cross-linguistic proficiency, and answer reproducibility, accompanied by statistical analysis. The findings demonstrate that the model performs consistently, regardless of whether prompts include a role definition or not. In addition, its adaptability across languages is confirmed by maintaining stable accuracy in both original and translated datasets. A distinct contrast emerges between its performance on lower-order factual recall tasks and higher-order reasoning exercises, which underscores its strengths in retrieving information and its limitations in complex analytical tasks. Although DeepSeek-V3 offers considerable practical value for network security education, challenges remain in its capability to process multimodal data and address highly intricate topics. These results provide valuable insights for future refinement of large language models in specialized professional environments.