A central challenge in reinforcement learning (RL) is its dependence on extensive real-world interaction data to learn task-specific policies. While recent work demonstrates that large language models (LLMs) can mitigate this limitation by generating synthetic experience (noted as imaginary rollouts) for mastering novel tasks, progress in this emerging field is hindered due to the lack of a standard benchmark. To bridge this gap, we introduce ImagineBench, the first comprehensive benchmark for evaluating offline RL algorithms that leverage both real rollouts and LLM-imaginary rollouts. The key features of ImagineBench include: (1) datasets comprising environment-collected and LLM-imaginary rollouts; (2) diverse domains of environments covering locomotion, robotic manipulation, and navigation tasks; and (3) natural language task instructions with varying complexity levels to facilitate language-conditioned policy learning. Through systematic evaluation of state-of-the-art offline RL algorithms, we observe that simply applying existing offline RL algorithms leads to suboptimal performance on unseen tasks, achieving 35.44% success rate in hard tasks in contrast to 64.37% of method training on real rollouts for hard tasks. This result highlights the need for algorithm advancements to better leverage LLM-imaginary rollouts. Additionally, we identify key opportunities for future research: including better utilization of imaginary rollouts, fast online adaptation and continual learning, and extension to multi-modal tasks. Our code is publicly available at https://github.com/LAMDA-RL/ImagineBench.
Designing a 6G-oriented universal model capable of processing multi-modal data and executing diverse air interface tasks has emerged as a common goal in future wireless systems. Building on our prior work in communication multi-modal alignment and telecom large language model (LLM), we propose a scalable, task-aware artificial intelligence-air interface multi-modal universal model (AI2MMUM), which flexibility and effectively perform various physical layer tasks according to subtle task instructions. The LLM backbone provides robust contextual comprehension and generalization capabilities, while a fine-tuning approach is adopted to incorporate domain-specific knowledge. To enhance task adaptability, task instructions consist of fixed task keywords and learnable, implicit prefix prompts. Frozen radio modality encoders extract universal representations and adapter layers subsequently bridge radio and language modalities. Moreover, lightweight task-specific heads are designed to directly output task objectives. Comprehensive evaluations demonstrate that AI2MMUM achieves SOTA performance across five representative physical environment/wireless channel-based downstream tasks using the WAIR-D and DeepMIMO datasets.
Understanding the factors contributing to traffic crashes and developing strategies to mitigate their severity is essential. Traditional statistical methods and machine learning models often struggle to capture the complex interactions between various factors and the unique characteristics of each crash. This research leverages large language model (LLM) to analyze freeway crash data and provide crash causation analysis accordingly. By compiling 226 traffic safety studies related to freeway crashes, a training dataset encompassing environmental, driver, traffic, and geometric design factors was created. The Llama3 8B model was fine-tuned using QLoRA to enhance its understanding of freeway crashes and their contributing factors, as covered in these studies. The fine-tuned Llama3 8B model was then used to identify crash causation without pre-labeled data through zero-shot classification, providing comprehensive explanations to ensure that the identified causes were reasonable and aligned with existing research. Results demonstrate that LLMs effectively identify primary crash causes such as alcohol-impaired driving, speeding, aggressive driving, and driver inattention. Incorporating event data, such as road maintenance, offers more profound insights. The model's practical applicability and potential to improve traffic safety measures were validated by a high level of agreement among researchers in the field of traffic safety, as reflected in questionnaire results with 88.89%. This research highlights the complex nature of traffic crashes and how LLMs can be used for comprehensive analysis of crash causation and other contributing factors. Moreover, it provides valuable insights and potential countermeasures to aid planners and policymakers in developing more effective and efficient traffic safety practices.
We directly compare the persuasion capabilities of a frontier large language model (LLM; Claude Sonnet 3.5) against incentivized human persuaders in an interactive, real-time conversational quiz setting. In this preregistered, large-scale incentivized experiment, participants (quiz takers) completed an online quiz where persuaders (either humans or LLMs) attempted to persuade quiz takers toward correct or incorrect answers. We find that LLM persuaders achieved significantly higher compliance with their directional persuasion attempts than incentivized human persuaders, demonstrating superior persuasive capabilities in both truthful (toward correct answers) and deceptive (toward incorrect answers) contexts. We also find that LLM persuaders significantly increased quiz takers' accuracy, leading to higher earnings, when steering quiz takers toward correct answers, and significantly decreased their accuracy, leading to lower earnings, when steering them toward incorrect answers. Overall, our findings suggest that AI's persuasion capabilities already exceed those of humans that have real-money bonuses tied to performance. Our findings of increasingly capable AI persuaders thus underscore the urgency of emerging alignment and governance frameworks.
Clustering patient subgroups is essential for personalized care and efficient resource use. Traditional clustering methods struggle with high-dimensional, heterogeneous healthcare data and lack contextual understanding. This study evaluates Large Language Model (LLM) based clustering against classical methods using a pediatric sepsis dataset from a low-income country (LIC), containing 2,686 records with 28 numerical and 119 categorical variables. Patient records were serialized into text with and without a clustering objective. Embeddings were generated using quantized LLAMA 3.1 8B, DeepSeek-R1-Distill-Llama-8B with low-rank adaptation(LoRA), and Stella-En-400M-V5 models. K-means clustering was applied to these embeddings. Classical comparisons included K-Medoids clustering on UMAP and FAMD-reduced mixed data. Silhouette scores and statistical tests evaluated cluster quality and distinctiveness. Stella-En-400M-V5 achieved the highest Silhouette Score (0.86). LLAMA 3.1 8B with the clustering objective performed better with higher number of clusters, identifying subgroups with distinct nutritional, clinical, and socioeconomic profiles. LLM-based methods outperformed classical techniques by capturing richer context and prioritizing key features. These results highlight potential of LLMs for contextual phenotyping and informed decision-making in resource-limited settings.
The recent trend of self-sovereign Decentralized AI Agents (DeAgents) combines Large Language Model (LLM)-based AI agents with decentralization technologies such as blockchain smart contracts and trusted execution environments (TEEs). These tamper-resistant trustless substrates allow agents to achieve self-sovereignty through ownership of cryptowallet private keys and control of digital assets and social media accounts. DeAgent eliminates centralized control and reduces human intervention, addressing key trust concerns inherent in centralized AI systems. However, given ongoing challenges in LLM reliability such as hallucinations, this creates paradoxical tension between trustlessness and unreliable autonomy. This study addresses this empirical research gap through interviews with DeAgents stakeholders-experts, founders, and developers-to examine their motivations, benefits, and governance dilemmas. The findings will guide future DeAgents system and protocol design and inform discussions about governance in sociotechnical AI systems in the future agentic web.
Location Intelligence (LI), the science of transforming location-centric geospatial data into actionable knowledge, has become a cornerstone of modern spatial decision-making. The rapid evolution of Geospatial Representation Learning is fundamentally reshaping LI development through two successive technological revolutions: the deep learning breakthrough and the emerging large language model (LLM) paradigm. While deep neural networks (DNNs) have demonstrated remarkable success in automated feature extraction from structured geospatial data (e.g., satellite imagery, GPS trajectories), the recent integration of LLMs introduces transformative capabilities for cross-modal geospatial reasoning and unstructured geo-textual data processing. This survey presents a comprehensive review of geospatial representation learning across both technological eras, organizing them into a structured taxonomy based on the complete pipeline comprising: (1) data perspective, (2) methodological perspective and (3) application perspective. We also highlight current advancements, discuss existing limitations, and propose potential future research directions in the LLM era. This work offers a thorough exploration of the field and providing a roadmap for further innovation in LI. The summary of the up-to-date paper list can be found in https://github.com/CityMind-Lab/Awesome-Location-Intelligence and will undergo continuous updates.
Beyond neural scaling laws, little is known about the laws underlying large language models (LLMs). We introduce Neural Thermodynamic Laws (NTL) -- a new framework that offers fresh insights into LLM training dynamics. On the theoretical side, we demonstrate that key thermodynamic quantities (e.g., temperature, entropy, heat capacity, thermal conduction) and classical thermodynamic principles (e.g., the three laws of thermodynamics and the equipartition theorem) naturally emerge under river-valley loss landscape assumptions. On the practical side, this scientific perspective yields intuitive guidelines for designing learning rate schedules.
With the development of photorealistic diffusion models, models trained in part or fully on synthetic data achieve progressively better results. However, diffusion models still routinely generate images that would not exist in reality, such as a dog floating above the ground or with unrealistic texture artifacts. We define the concept of feasibility as whether attributes in a synthetic image could realistically exist in the real-world domain; synthetic images containing attributes that violate this criterion are considered infeasible. Intuitively, infeasible images are typically considered out-of-distribution; thus, training on such images is expected to hinder a model's ability to generalize to real-world data, and they should therefore be excluded from the training set whenever possible. However, does feasibility really matter? In this paper, we investigate whether enforcing feasibility is necessary when generating synthetic training data for CLIP-based classifiers, focusing on three target attributes: background, color, and texture. We introduce VariReal, a pipeline that minimally edits a given source image to include feasible or infeasible attributes given by the textual prompt generated by a large language model. Our experiments show that feasibility minimally affects LoRA-fine-tuned CLIP performance, with mostly less than 0.3% difference in top-1 accuracy across three fine-grained datasets. Also, the attribute matters on whether the feasible/infeasible images adversarially influence the classification performance. Finally, mixing feasible and infeasible images in training datasets does not significantly impact performance compared to using purely feasible or infeasible datasets.
While large language models demonstrate impressive performance on static benchmarks, the true potential of large language models as self-learning and reasoning agents in dynamic environments remains unclear. This study systematically evaluates the efficacy of self-reflection, heuristic mutation, and planning as prompting techniques to test the adaptive capabilities of agents. We conduct experiments with various open-source language models in dynamic environments and find that larger models generally outperform smaller ones, but that strategic prompting can close this performance gap. Second, a too-long prompt can negatively impact smaller models on basic reactive tasks, while larger models show more robust behaviour. Third, advanced prompting techniques primarily benefit smaller models on complex games, but offer less improvement for already high-performing large language models. Yet, we find that advanced reasoning methods yield highly variable outcomes: while capable of significantly improving performance when reasoning and decision-making align, they also introduce instability and can lead to big performance drops. Compared to human performance, our findings reveal little evidence of true emergent reasoning. Instead, large language model performance exhibits persistent limitations in crucial areas such as planning, reasoning, and spatial coordination, suggesting that current-generation large language models still suffer fundamental shortcomings that may not be fully overcome through self-reflective prompting alone. Reasoning is a multi-faceted task, and while reasoning methods like Chain of thought improves multi-step reasoning on math word problems, our findings using dynamic benchmarks highlight important shortcomings in general reasoning capabilities, indicating a need to move beyond static benchmarks to capture the complexity of reasoning.
Our goal is to understand how post-training methods, such as fine-tuning, alignment, and unlearning, modify language model behavior and representations. We are particularly interested in the brittle nature of these modifications that makes them easy to bypass through prompt engineering or relearning. Recent results suggest that post-training induces shallow context-dependent ``circuits'' that suppress specific response patterns. This could be one explanation for the brittleness of post-training. To test this hypothesis, we design an unlearning algorithm, Layered Unlearning (LU), that creates distinct inhibitory mechanisms for a growing subset of the data. By unlearning the first $i$ folds while retaining the remaining $k - i$ at the $i$th of $k$ stages, LU limits the ability of relearning on a subset of data to recover the full dataset. We evaluate LU through a combination of synthetic and large language model (LLM) experiments. We find that LU improves robustness to adversarial relearning for several different unlearning methods. Our results contribute to the state-of-the-art of machine unlearning and provide insight into the effect of post-training updates.
I develop Ornithologist, a weakly-supervised textual classification system and measure the hawkishness and dovishness of central bank text. Ornithologist uses ``taxonomy-guided reasoning'', guiding a large language model with human-authored decision trees. This increases the transparency and explainability of the system and makes it accessible to non-experts. It also reduces hallucination risk. Since it requires less supervision than traditional classification systems, it can more easily be applied to other problems or sources of text (e.g. news) without much modification. Ornithologist measurements of hawkishness and dovishness of RBA communication carry information about the future of the cash rate path and of market expectations.
Large Language Models (LLMs) represent a major step toward artificial general intelligence, significantly advancing our ability to interact with technology. While LLMs perform well on Natural Language Processing tasks -- such as translation, generation, code writing, and summarization -- questions remain about their output similarity, variability, and ethical implications. For instance, how similar are texts generated by the same model? How does this compare across different models? And which models best uphold ethical standards? To investigate, we used 5{,}000 prompts spanning diverse tasks like generation, explanation, and rewriting. This resulted in approximately 3 million texts from 12 LLMs, including proprietary and open-source systems from OpenAI, Google, Microsoft, Meta, and Mistral. Key findings include: (1) outputs from the same LLM are more similar to each other than to human-written texts; (2) models like WizardLM-2-8x22b generate highly similar outputs, while GPT-4 produces more varied responses; (3) LLM writing styles differ significantly, with Llama 3 and Mistral showing higher similarity, and GPT-4 standing out for distinctiveness; (4) differences in vocabulary and tone underscore the linguistic uniqueness of LLM-generated content; (5) some LLMs demonstrate greater gender balance and reduced bias. These results offer new insights into the behavior and diversity of LLM outputs, helping guide future development and ethical evaluation.
Introduction: Timely identification of intracranial hemorrhage (ICH) subtypes on non-contrast computed tomography is critical for prognosis prediction and therapeutic decision-making, yet remains challenging due to low contrast and blurring boundaries. This study evaluates the performance of zero-shot multi-modal large language models (MLLMs) compared to traditional deep learning methods in ICH binary classification and subtyping. Methods: We utilized a dataset provided by RSNA, comprising 192 NCCT volumes. The study compares various MLLMs, including GPT-4o, Gemini 2.0 Flash, and Claude 3.5 Sonnet V2, with conventional deep learning models, including ResNet50 and Vision Transformer. Carefully crafted prompts were used to guide MLLMs in tasks such as ICH presence, subtype classification, localization, and volume estimation. Results: The results indicate that in the ICH binary classification task, traditional deep learning models outperform MLLMs comprehensively. For subtype classification, MLLMs also exhibit inferior performance compared to traditional deep learning models, with Gemini 2.0 Flash achieving an macro-averaged precision of 0.41 and a macro-averaged F1 score of 0.31. Conclusion: While MLLMs excel in interactive capabilities, their overall accuracy in ICH subtyping is inferior to deep networks. However, MLLMs enhance interpretability through language interactions, indicating potential in medical imaging analysis. Future efforts will focus on model refinement and developing more precise MLLMs to improve performance in three-dimensional medical image processing.
Vision-language models (VLMs) offer flexible object detection through natural language prompts but suffer from performance variability depending on prompt phrasing. In this paper, we introduce a method for automated prompt refinement using a novel metric called the Contrastive Class Alignment Score (CCAS), which ranks prompts based on their semantic alignment with a target object class while penalizing similarity to confounding classes. Our method generates diverse prompt candidates via a large language model and filters them through CCAS, computed using prompt embeddings from a sentence transformer. We evaluate our approach on challenging object categories, demonstrating that our automatic selection of high-precision prompts improves object detection accuracy without the need for additional model training or labeled data. This scalable and model-agnostic pipeline offers a principled alternative to manual prompt engineering for VLM-based detection systems.
This paper describes an approach to improve code comments along different quality axes by rewriting those comments with customized Artificial Intelligence (AI)-based tools. We conduct an empirical study followed by grounded theory qualitative analysis to determine the quality axes to improve. Then we propose a procedure using a Large Language Model (LLM) to rewrite existing code comments along the quality axes. We implement our procedure using GPT-4o, then distil the results into a smaller model capable of being run in-house, so users can maintain data custody. We evaluate both our approach using GPT-4o and the distilled model versions. We show in an evaluation how our procedure improves code comments along the quality axes. We release all data and source code in an online repository for reproducibility.
In standard large vision-language models (LVLMs) pre-training, the model typically maximizes the joint probability of the caption conditioned on the image via next-token prediction (NTP); however, since only a small subset of caption tokens directly relates to the visual content, this naive NTP unintentionally fits the model to noise and increases the risk of hallucination. We present PRIOR, a simple vision-language pre-training approach that addresses this issue by prioritizing image-related tokens through differential weighting in the NTP loss, drawing from the importance sampling framework. PRIOR introduces a reference model-a text-only large language model (LLM) trained on the captions without image inputs, to weight each token based on its probability for LVLMs training. Intuitively, tokens that are directly related to the visual inputs are harder to predict without the image and thus receive lower probabilities from the text-only reference LLM. During training, we implement a token-specific re-weighting term based on the importance scores to adjust each token's loss. We implement PRIOR in two distinct settings: LVLMs with visual encoders and LVLMs without visual encoders. We observe 19% and 8% average relative improvement, respectively, on several vision-language benchmarks compared to NTP. In addition, PRIOR exhibits superior scaling properties, as demonstrated by significantly higher scaling coefficients, indicating greater potential for performance gains compared to NTP given increasing compute and data.
Cell type annotation is a critical yet laborious step in single-cell RNA sequencing analysis. We present a trustworthy large language model (LLM)-agent, CellTypeAgent, which integrates LLMs with verification from relevant databases. CellTypeAgent achieves higher accuracy than existing methods while mitigating hallucinations. We evaluated CellTypeAgent across nine real datasets involving 303 cell types from 36 tissues. This combined approach holds promise for more efficient and reliable cell type annotation.
The use of Large Language Models (LLMs) in hardware design has taken off in recent years, principally through its incorporation in tools that increase chip designer productivity. There has been considerable discussion about the use of LLMs in RTL specifications of chip designs, for which the two most popular languages are Verilog and VHDL. LLMs and their use in Verilog design has received significant attention due to the higher popularity of the language, but little attention so far has been given to VHDL despite its continued popularity in the industry. There has also been little discussion about the unique needs of organizations that engage in high-performance processor design, and techniques to deploy AI solutions in these settings. In this paper, we describe our journey in developing a Large Language Model (LLM) specifically for the purpose of explaining VHDL code, a task that has particular importance in an organization with decades of experience and assets in high-performance processor design. We show how we developed test sets specific to our needs and used them for evaluating models as we performed extended pretraining (EPT) of a base LLM. Expert evaluation of the code explanations produced by the EPT model increased to 69% compared to a base model rating of 43%. We further show how we developed an LLM-as-a-judge to gauge models similar to expert evaluators. This led us to deriving and evaluating a host of new models, including an instruction-tuned version of the EPT model with an expected expert evaluator rating of 71%. Our experiments also indicate that with the potential use of newer base models, this rating can be pushed to 85% and beyond. We conclude with a discussion on further improving the quality of hardware design LLMs using exciting new developments in the Generative AI world.
Typhoon trajectory forecasting is essential for disaster preparedness but remains computationally demanding due to the complexity of atmospheric dynamics and the resource requirements of deep learning models. Quantum-Train (QT), a hybrid quantum-classical framework that leverages quantum neural networks (QNNs) to generate trainable parameters exclusively during training, eliminating the need for quantum hardware at inference time. Building on QT's success across multiple domains, including image classification, reinforcement learning, flood prediction, and large language model (LLM) fine-tuning, we introduce Quantum Parameter Adaptation (QPA) for efficient typhoon forecasting model learning. Integrated with an Attention-based Multi-ConvGRU model, QPA enables parameter-efficient training while maintaining predictive accuracy. This work represents the first application of quantum machine learning (QML) to large-scale typhoon trajectory prediction, offering a scalable and energy-efficient approach to climate modeling. Our results demonstrate that QPA significantly reduces the number of trainable parameters while preserving performance, making high-performance forecasting more accessible and sustainable through hybrid quantum-classical learning.