Aerial Vision-and-Language Navigation (VLN) is a novel task enabling Unmanned Aerial Vehicles (UAVs) to navigate in outdoor environments through natural language instructions and visual cues. It remains challenging due to the complex spatial relationships in outdoor aerial scenes. In this paper, we propose an end-to-end zero-shot framework for aerial VLN tasks, where the large language model (LLM) is introduced as our agent for action prediction. Specifically, we develop a novel Semantic-Topo-Metric Representation (STMR) to enhance the spatial reasoning ability of LLMs. This is achieved by extracting and projecting instruction-related semantic masks of landmarks into a top-down map that contains the location information of surrounding landmarks. Further, this map is transformed into a matrix representation with distance metrics as the text prompt to the LLM, for action prediction according to the instruction. Experiments conducted in real and simulation environments have successfully proved the effectiveness and robustness of our method, achieving 15.9% and 12.5% improvements (absolute) in Oracle Success Rate (OSR) on AerialVLN-S dataset.
This paper presents $\forall$uto$\exists$$\lor\!\land$L, a novel benchmark for scaling Large Language Model (LLM) assessment in formal tasks with clear notions of correctness, such as truth maintenance in translation and logical reasoning. $\forall$uto$\exists$$\lor\!\land$L is the first benchmarking paradigm that offers several key advantages necessary for scaling objective evaluation of LLMs without human labeling: (a) ability to evaluate LLMs of increasing sophistication by auto-generating tasks at different levels of difficulty; (b) auto-generation of ground truth that eliminates dependence on expensive and time-consuming human annotation; (c) the use of automatically generated, randomized datasets that mitigate the ability of successive LLMs to overfit to static datasets used in many contemporary benchmarks. Empirical analysis shows that an LLM's performance on $\forall$uto$\exists$$\lor\!\land$L is highly indicative of its performance on a diverse array of other benchmarks focusing on translation and reasoning tasks, making it a valuable autonomous evaluation paradigm in settings where hand-curated datasets can be hard to obtain and/or update.
The emerging field of AI-generated art has witnessed the rise of prompt marketplaces, where creators can purchase, sell, or share prompts for generating unique artworks. These marketplaces often assert ownership over prompts, claiming them as intellectual property. This paper investigates whether concealed prompts sold on prompt marketplaces can be considered as secure intellectual property, given that humans and AI tools may be able to approximately infer the prompts based on publicly advertised sample images accompanying each prompt on sale. Specifically, our survey aims to assess (i) how accurately can humans infer the original prompt solely by examining an AI-generated image, with the goal of generating images similar to the original image, and (ii) the possibility of improving upon individual human and AI prompt inferences by crafting human-AI combined prompts with the help of a large language model. Although previous research has explored the use of AI and machine learning to infer (and also protect against) prompt inference, we are the first to include humans in the loop. Our findings indicate that while humans and human-AI collaborations can infer prompts and generate similar images with high accuracy, they are not as successful as using the original prompt.
Logical errors in programming don't raise compiler alerts, making them hard to detect. These silent errors can disrupt a program's function or cause run-time issues. Their correction requires deep insight into the program's logic, highlighting the importance of automated detection and repair. In this paper, we introduce LecPrompt to localize and repair logical errors, an prompt-based approach that harnesses the capabilities of CodeBERT, a transformer-based large language model trained on code. First, LecPrompt leverages a large language model to calculate perplexity and log probability metrics, pinpointing logical errors at both token and line levels. Through statistical analysis, it identifies tokens and lines that deviate significantly from the expected patterns recognized by large language models, marking them as potential error sources. Second, by framing the logical error correction challenge as a Masked Language Modeling (MLM) task, LecPrompt employs CodeBERT to autoregressively repair the identified error tokens. Finally, the soft-prompt method provides a novel solution in low-cost scenarios, ensuring that the model can be fine-tuned to the specific nuances of the logical error correction task without incurring high computational costs. To evaluate LecPrompt's performance, we created a method to introduce logical errors into correct code and applying this on QuixBugs to produce the QuixBugs-LE dataset. Our evaluations on the QuixBugs-LE dataset for both Python and Java highlight the impressive capabilities of our method, LecPrompt. For Python, LecPrompt achieves a noteworthy 74.58% top-1 token-level repair accuracy and 27.4% program-level repair accuracy. In Java, LecPrompt delivers a 69.23\% top-1 token-level repair accuracy and 24.7% full program-level repair accuracy.
Ptychography is an advanced computational imaging technique in X-ray and electron microscopy. It has been widely adopted across scientific research fields, including physics, chemistry, biology, and materials science, as well as in industrial applications such as semiconductor characterization. In practice, obtaining high-quality ptychographic images requires simultaneous optimization of numerous experimental and algorithmic parameters. Traditionally, parameter selection often relies on trial and error, leading to low-throughput workflows and potential human bias. In this work, we develop the "Ptychographic Experiment and Analysis Robot" (PEAR), a framework that leverages large language models (LLMs) to automate data analysis in ptychography. To ensure high robustness and accuracy, PEAR employs multiple LLM agents for tasks including knowledge retrieval, code generation, parameter recommendation, and image reasoning. Our study demonstrates that PEAR's multi-agent design significantly improves the workflow success rate, even with smaller open-weight models such as LLaMA 3.1 8B. PEAR also supports various automation levels and is designed to work with customized local knowledge bases, ensuring flexibility and adaptability across different research environments.
Social conventions are the backbone of social coordination, shaping how individuals form a group. As growing populations of artificial intelligence (AI) agents communicate through natural language, a fundamental question is whether they can bootstrap the foundations of a society. Here, we present experimental results that demonstrate the spontaneous emergence of universally adopted social conventions in decentralized populations of large language model (LLM) agents. We then show how strong collective biases can emerge during this process, even when agents exhibit no bias individually. Last, we examine how committed minority groups of adversarial LLM agents can drive social change by imposing alternative social conventions on the larger population. Our results show that AI systems can autonomously develop social conventions without explicit programming and have implications for designing AI systems that align, and remain aligned, with human values and societal goals.
Preference learning is a central component for aligning current LLMs, but this process can be vulnerable to data poisoning attacks. To address this concern, we introduce PoisonBench, a benchmark for evaluating large language models' susceptibility to data poisoning during preference learning. Data poisoning attacks can manipulate large language model responses to include hidden malicious content or biases, potentially causing the model to generate harmful or unintended outputs while appearing to function normally. We deploy two distinct attack types across eight realistic scenarios, assessing 21 widely-used models. Our findings reveal concerning trends: (1) Scaling up parameter size does not inherently enhance resilience against poisoning attacks; (2) There exists a log-linear relationship between the effects of the attack and the data poison ratio; (3) The effect of data poisoning can generalize to extrapolated triggers that are not included in the poisoned data. These results expose weaknesses in current preference learning techniques, highlighting the urgent need for more robust defenses against malicious models and data manipulation.
Specimen associated biodiversity data are sought after for biological, environmental, climate, and conservation sciences. A rate shift is required for the extraction of data from specimen images to eliminate the bottleneck that the reliance on human-mediated transcription of these data represents. We applied advanced computer vision techniques to develop the `Hespi' (HErbarium Specimen sheet PIpeline), which extracts a pre-catalogue subset of collection data on the institutional labels on herbarium specimens from their digital images. The pipeline integrates two object detection models; the first detects bounding boxes around text-based labels and the second detects bounding boxes around text-based data fields on the primary institutional label. The pipeline classifies text-based institutional labels as printed, typed, handwritten, or a combination and applies Optical Character Recognition (OCR) and Handwritten Text Recognition (HTR) for data extraction. The recognized text is then corrected against authoritative databases of taxon names. The extracted text is also corrected with the aide of a multimodal Large Language Model (LLM). Hespi accurately detects and extracts text for test datasets including specimen sheet images from international herbaria. The components of the pipeline are modular and users can train their own models with their own data and use them in place of the models provided.
The increasing number of dispersed EEG dataset publications and the advancement of large-scale Electroencephalogram (EEG) models have increased the demand for practical tools to manage diverse EEG datasets. However, the inherent complexity of EEG data, characterized by variability in content data, metadata, and data formats, poses challenges for integrating multiple datasets and conducting large-scale EEG model research. To tackle the challenges, this paper introduces EEGUnity, an open-source tool that incorporates modules of 'EEG Parser', 'Correction', 'Batch Processing', and 'Large Language Model Boost'. Leveraging the functionality of such modules, EEGUnity facilitates the efficient management of multiple EEG datasets, such as intelligent data structure inference, data cleaning, and data unification. In addition, the capabilities of EEGUnity ensure high data quality and consistency, providing a reliable foundation for large-scale EEG data research. EEGUnity is evaluated across 25 EEG datasets from different sources, offering several typical batch processing workflows. The results demonstrate the high performance and flexibility of EEGUnity in parsing and data processing. The project code is publicly available at github.com/Baizhige/EEGUnity.
Complex logical reasoning tasks require a long sequence of reasoning, which a large language model (LLM) with chain-of-thought prompting still falls short. To alleviate this issue, neurosymbolic approaches incorporate a symbolic solver. Specifically, an LLM only translates a natural language problem into a satisfiability (SAT) problem that consists of first-order logic formulas, and a sound symbolic solver returns a mathematically correct solution. However, we discover that LLMs have difficulties to capture complex logical semantics hidden in the natural language during translation. To resolve this limitation, we propose a Compositional First-Order Logic Translation. An LLM first parses a natural language sentence into newly defined logical dependency structures that consist of an atomic subsentence and its dependents, then sequentially translate the parsed subsentences. Since multiple logical dependency structures and sequential translations are possible for a single sentence, we also introduce two Verification algorithms to ensure more reliable results. We utilize an SAT solver to rigorously compare semantics of generated first-order logic formulas and select the most probable one. We evaluate the proposed method, dubbed CLOVER, on seven logical reasoning benchmarks and show that it outperforms the previous neurosymbolic approaches and achieves new state-of-the-art results.
Knowledge editing has been proposed as an effective method for updating and correcting the internal knowledge of Large Language Models (LLMs). However, existing editing methods often struggle with complex tasks, such as multi-hop reasoning. In this paper, we identify and investigate the phenomenon of Editing Overfit, where edited models assign disproportionately high probabilities to the edit target, hindering the generalization of new knowledge in complex scenarios. We attribute this issue to the current editing paradigm, which places excessive emphasis on the direct correspondence between the input prompt and the edit target for each edit sample. To further explore this issue, we introduce a new benchmark, EVOKE (EValuation of Editing Overfit in Knowledge Editing), along with fine-grained evaluation metrics. Through comprehensive experiments and analysis, we demonstrate that Editing Overfit is prevalent in current editing methods and that common overfitting mitigation strategies are of limited effectiveness in knowledge editing. To overcome this, inspired by LLMs' knowledge recall mechanisms, we propose a new plug-and-play strategy called Learn to Inference (LTI), which introduce a Multi-stage Inference Constraint module to guide the edited models in recalling new knowledge similarly to how unedited LLMs leverage knowledge through in-context learning. Extensive experimental results across a wide range of tasks validate the effectiveness of LTI in mitigating Editing Overfit.
Background: Machine learning methods for clinical named entity recognition and entity normalization systems can utilize both labeled corpora and Knowledge Graphs (KGs) for learning. However, infrequently occurring concepts may have few mentions in training corpora and lack detailed descriptions or synonyms, even in large KGs. For Disease Entity Recognition (DER) and Disease Entity Normalization (DEN), this can result in fewer high quality training examples relative to the number of known diseases. Large Language Model (LLM) generation of synthetic training examples could improve performance in these information extraction tasks. Methods: We fine-tuned a LLaMa-2 13B Chat LLM to generate a synthetic corpus containing normalized mentions of concepts from the Unified Medical Language System (UMLS) Disease Semantic Group. We measured overall and Out of Distribution (OOD) performance for DER and DEN, with and without synthetic data augmentation. We evaluated performance on 3 different disease corpora using 4 different data augmentation strategies, assessed using BioBERT for DER and SapBERT and KrissBERT for DEN. Results: Our synthetic data yielded a substantial improvement for DEN, in all 3 training corpora the top 1 accuracy of both SapBERT and KrissBERT improved by 3-9 points in overall performance and by 20-55 points in OOD data. A small improvement (1-2 points) was also seen for DER in overall performance, but only one dataset showed OOD improvement. Conclusion: LLM generation of normalized disease mentions can improve DEN relative to normalization approaches that do not utilize LLMs to augment data with synthetic mentions. Ablation studies indicate that performance gains for DEN were only partially attributable to improvements in OOD performance. The same approach has only a limited ability to improve DER. We make our software and dataset publicly available.
In sequential decision-making (SDM) tasks, methods like reinforcement learning (RL) and heuristic search have made notable advances in specific cases. However, they often require extensive exploration and face challenges in generalizing across diverse environments due to their limited grasp of the underlying decision dynamics. In contrast, large language models (LLMs) have recently emerged as powerful general-purpose tools, due to their capacity to maintain vast amounts of domain-specific knowledge. To harness this rich prior knowledge for efficiently solving complex SDM tasks, we propose treating LLMs as prior action distributions and integrating them into RL frameworks through Bayesian inference methods, making use of variational inference and direct posterior sampling. The proposed approaches facilitate the seamless incorporation of fixed LLM priors into both policy-based and value-based RL frameworks. Our experiments show that incorporating LLM-based action priors significantly reduces exploration and optimization complexity, substantially improving sample efficiency compared to traditional RL techniques, e.g., using LLM priors decreases the number of required samples by over 90% in offline learning scenarios.
Large Language Model (LLM) services exhibit impressive capability on unlearned tasks leveraging only a few examples by in-context learning (ICL). However, the success of ICL varies depending on the task and context, leading to heterogeneous service quality. Directly estimating the performance of LLM services at each invocation can be laborious, especially requiring abundant labeled data or internal information within the LLM. This paper introduces a novel method to estimate the performance of LLM services across different tasks and contexts, which can be "plug-and-play" utilizing only a few unlabeled samples like ICL. Our findings suggest that the negative log-likelihood and perplexity derived from LLM service invocation can function as effective and significant features. Based on these features, we utilize four distinct meta-models to estimate the performance of LLM services. Our proposed method is compared against unlabeled estimation baselines across multiple LLM services and tasks. And it is experimentally applied to two scenarios, demonstrating its effectiveness in the selection and further optimization of LLM services.
Post-Training Quantization (PTQ) is an effective technique for compressing Large Language Models (LLMs). While many studies focus on quantizing both weights and activations, it is still a challenge to maintain the accuracy of LLM after activating quantization. To investigate the primary cause, we extend the concept of kernel from linear algebra to quantization functions to define a new term, "quantization kernel", which refers to the set of elements in activations that are quantized to zero. Through quantitative analysis of the quantization kernel, we find that these elements are crucial for maintaining the accuracy of quantized LLMs. With the decrease of quantization kernel, the precision of quantized LLMs increases. If the quantization kernel proportion is kept below 19% for OPT models and below 1% for LLaMA models, the precision loss from quantizing activations to INT8 becomes negligible. Motivated by the goal of developing a quantization method with small quantization kernel, we propose CrossQuant: a simple yet effective method for quantizing activations. CrossQuant cross-quantizes elements using row and column-wise absolute maximum vectors, achieving a quantization kernel of approximately 16% for OPT models and less than 0.1% for LLaMA models. Experimental results on LLMs (LLaMA, OPT) ranging from 6.7B to 70B parameters demonstrate that CrossQuant improves or maintains perplexity and accuracy in language modeling, zero-shot, and few-shot tasks.
In recent years, with the maturation of large language model (LLM) technology and the emergence of high-quality programming code datasets, researchers have become increasingly confident in addressing the challenges of program synthesis automatically. However, since most of the training samples for LLMs are unscreened, it is inevitable that LLMs' performance may not align with real-world scenarios, leading to the presence of social bias. To evaluate and quantify the gender bias in code LLMs, we propose a dataset named CodeGenBias (Gender Bias in the Code Generation) and an evaluation metric called FB-Score (Factual Bias Score) based on the actual gender distribution of correlative professions. With the help of CodeGenBias and FB-Score, we evaluate and analyze the gender bias in eight mainstream Code LLMs. Previous work has demonstrated that model editing methods that perform well in knowledge editing have the potential to mitigate social bias in LLMs. Therefore, we develop a model editing approach named MG-Editing (Multi-Granularity model Editing), which includes the locating and editing phases. Our model editing method MG-Editing can be applied at five different levels of model parameter granularity: full parameters level, layer level, module level, row level, and neuron level. Extensive experiments not only demonstrate that our MG-Editing can effectively mitigate the gender bias in code LLMs while maintaining their general code generation capabilities, but also showcase its excellent generalization. At the same time, the experimental results show that, considering both the gender bias of the model and its general code generation capability, MG-Editing is most effective when applied at the row and neuron levels of granularity.
Entity Linking (EL) is the process of associating ambiguous textual mentions to specific entities in a knowledge base. Traditional EL methods heavily rely on large datasets to enhance their performance, a dependency that becomes problematic in the context of few-shot entity linking, where only a limited number of examples are available for training. To address this challenge, we present OneNet, an innovative framework that utilizes the few-shot learning capabilities of Large Language Models (LLMs) without the need for fine-tuning. To the best of our knowledge, this marks a pioneering approach to applying LLMs to few-shot entity linking tasks. OneNet is structured around three key components prompted by LLMs: (1) an entity reduction processor that simplifies inputs by summarizing and filtering out irrelevant entities, (2) a dual-perspective entity linker that combines contextual cues and prior knowledge for precise entity linking, and (3) an entity consensus judger that employs a unique consistency algorithm to alleviate the hallucination in the entity linking reasoning. Comprehensive evaluations across seven benchmark datasets reveal that OneNet outperforms current state-of-the-art entity linking methods.
Large Language Model (LLM) based multi-agent systems (MAS) show remarkable potential in collaborative problem-solving, yet they still face critical challenges: low communication efficiency, poor scalability, and a lack of effective parameter-updating optimization methods. We present Optima, a novel framework that addresses these issues by significantly enhancing both communication efficiency and task effectiveness in LLM-based MAS through LLM training. Optima employs an iterative generate, rank, select, and train paradigm with a reward function balancing task performance, token efficiency, and communication readability. We explore various RL algorithms, including Supervised Fine-Tuning, Direct Preference Optimization, and their hybrid approaches, providing insights into their effectiveness-efficiency trade-offs. We integrate Monte Carlo Tree Search-inspired techniques for DPO data generation, treating conversation turns as tree nodes to explore diverse interaction paths. Evaluated on common multi-agent tasks, including information-asymmetric question answering and complex reasoning, Optima shows consistent and substantial improvements over single-agent baselines and vanilla MAS based on Llama 3 8B, achieving up to 2.8x performance gain with less than 10\% tokens on tasks requiring heavy information exchange. Moreover, Optima's efficiency gains open new possibilities for leveraging inference-compute more effectively, leading to improved inference-time scaling laws. By addressing fundamental challenges in LLM-based MAS, Optima shows the potential towards scalable, efficient, and effective MAS (https://chenweize1998.github.io/optima-project-page).
Gene expression is a cellular process that plays a fundamental role in human phenotypical variations and diseases. Despite advances of deep learning models for gene expression prediction, recent benchmarks have revealed their inability to learn distal regulatory grammar. Here, we address this challenge by leveraging a pretrained large language model to enhance gene expression prediction. We introduce Genetic sequence Token Alignment (GTA), which aligns genetic sequence features with natural language tokens, allowing for symbolic reasoning of genomic sequence features via the frozen language model. This cross-modal adaptation learns the regulatory grammar and allows us to further incorporate gene-specific human annotations as prompts, enabling in-context learning that is not possible with existing models. Trained on lymphoblastoid cells, GTA was evaluated on cells from the Geuvadis consortium and outperforms state-of-the-art models such as Enformer, achieving a Spearman correlation of 0.65, a 10\% improvement. Additionally, GTA offers improved interpretation of long-range interactions through the identification of the most meaningful sections of the input genetic context. GTA represents a powerful and novel cross-modal approach to gene expression prediction by utilizing a pretrained language model, in a paradigm shift from conventional gene expression models trained only on sequence data.
Reliability in cell type annotation is challenging in single-cell RNA-sequencing data analysis because both expert-driven and automated methods can be biased or constrained by their training data, especially for novel or rare cell types. Although large language models (LLMs) are useful, our evaluation found that only a few matched expert annotations due to biased data sources and inflexible training inputs. To overcome these limitations, we developed the LICT (Large language model-based Identifier for Cell Types) software package using a multi-model fusion and "talk-to-machine" strategy. Tested across various single-cell RNA sequencing datasets, our approach significantly improved annotation reliability, especially in datasets with low cellular heterogeneity. Notably, we established objective criteria to assess annotation reliability using the "talk-to-machine" approach, which addresses discrepancies between our annotations and expert ones, enabling reliable evaluation even without reference data. This strategy enhances annotation credibility and sets the stage for advancing future LLM-based cell type annotation methods.