Mathematical discoveries from program search with large language models

Large language models (LLMs) have shown impressive capabilities across various natural language tasks. However, evaluating their alignment with human preferences remains a challenge. To this end, we propose a comprehensive human evaluation framework to assess LLMs’ proficiency in following instructions on diverse real-world tasks. We construct a hierarchical task tree encompassing 7 major areas covering over 200 categories and over 800 tasks, which covers diverse capabilities such as question answering, reasoning, multiturn dialogue, and text generation, to evaluate LLMs in a comprehensive and in-depth manner. We also design detailed evaluation standards and processes to facilitate consistent, unbiased judgments from human evaluators. A test set of over 3,000 instances is released, spanning different difficulty levels and knowledge domains. Our work provides a standardized methodology to evaluate human alignment in LLMs for both English and Chinese. We also analyze the feasibility of automating parts of evaluation with a strong LLM (GPT-4). Our framework supports a thorough assessment of LLMs as they are integrated into real-world applications. We have made publicly available the task tree, TencentLLMEval dataset, and evaluation methodology which have been demonstrated as effective in assessing the performance of Tencent Hunyuan LLMs 1 . By doing so, we aim to facilitate the benchmarking of advances in the development of safe and human-aligned LLMs.

BackgroundThe launch of ChatGPT (OpenAI) in November 2022 attracted public attention and academic interest to large language models (LLMs), facilitating the emergence of many other innovative LLMs. These LLMs have been applied in various fields, including health care. Numerous studies have since been conducted regarding how to use state-of-the-art LLMs in health-related scenarios.ObjectiveThis review aims to summarize applications of and concerns regarding conversational LLMs in health care and provide an agenda for future research in this field.MethodsWe used PubMed, ACM, and the IEEE digital libraries as primary sources for this review. We followed the guidance of PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) to screen and select peer-reviewed research articles that (1) were related to health care applications and conversational LLMs and (2) were published before September 1, 2023, the date when we started paper collection. We investigated these papers and classified them according to their applications and concerns.ResultsOur search initially identified 820 papers according to targeted keywords, out of which 65 (7.9%) papers met our criteria and were included in the review. The most popular conversational LLM was ChatGPT (60/65, 92% of papers), followed by Bard (Google LLC; 1/65, 2% of papers), LLaMA (Meta; 1/65, 2% of papers), and other LLMs (6/65, 9% papers). These papers were classified into four categories of applications: (1) summarization, (2) medical knowledge inquiry, (3) prediction (eg, diagnosis, treatment recommendation, and drug synergy), and (4) administration (eg, documentation and information collection), and four categories of concerns: (1) reliability (eg, training data quality, accuracy, interpretability, and consistency in responses), (2) bias, (3) privacy, and (4) public acceptability. There were 49 (75%) papers using LLMs for either summarization or medical knowledge inquiry, or both, and there are 58 (89%) papers expressing concerns about either reliability or bias, or both. We found that conversational LLMs exhibited promising results in summarization and providing general medical knowledge to patients with a relatively high accuracy. However, conversational LLMs such as ChatGPT are not always able to provide reliable answers to complex health-related tasks (eg, diagnosis) that require specialized domain expertise. While bias or privacy issues are often noted as concerns, no experiments in our reviewed papers thoughtfully examined how conversational LLMs lead to these issues in health care research.ConclusionsFuture studies should focus on improving the reliability of LLM applications in complex health-related tasks, as well as investigating the mechanisms of how LLM applications bring bias and privacy issues. Considering the vast accessibility of LLMs, legal, social, and technical efforts are all needed to address concerns about LLMs to promote, improve, and regularize the application of LLMs in health care.

The article presents a methodology for designing a benchmark to assess numerical reasoning skills in Large Language Models (LLMs). In the context of LLMs, numerical reasoning is defined as a model’s ability to correctly interpret, process, and utilize numerical information in text, including understanding magnitudes and relations between numbers, performing arithmetic operations, and generating numerals accurately in its outputs. The proposed methodology is based on decomposing applied tasks and enables targeted evaluation of specific facets of numerical reasoning using tasks that involve numerals. Particular attention is paid to the representation of numbers in textual prompts to LLMs, as this factor directly affects the quality of the final output. The need for rigorous assessment of LLMs’ numerical reasoning stems from its critical role across a wide range of text-centric applications, including automated summarization, generation of analytical reports, extraction and interpretation of quantitative data, and conversational systems operating on financial, scientific, or technical information. Drawing on an analysis of state-of-the-art LLM evaluation approaches, core principles for constructing evaluation benchmarks are formulated with an emphasis on generality and real-world applicability. In accordance with the proposed methodology, the MUE (Math Understanding Evaluation) benchmark is introduced; it comprises five test suites, each designed to assess a distinct aspect of LLM numerical reasoning. A comparative evaluation of popular LLMs is conducted, leading models are identified, and the strengths and weaknesses of their numerical reasoning are characterized. The findings are intended to inform LLM developers in refining architectures and training strategies, and to guide end users and integrators in selecting an optimal model for applied projects.

Extracting information from unstructured and semi-structured geoscience literature is a crucial step in conducting geological research. The traditional machine learning extraction paradigm requires a substantial amount of high-quality manually annotated data for model training, which is time-consuming, labor-intensive, and not easily transferable to new fields. Recently, large language models (LLMs) (e.g., ChatGPT, GPT-4, and LLaMA), have shown great performance in various natural language processing (NLP) tasks, such as question answering, machine translation, and text generation. A substantial body of work has demonstrated that LLMs possess strong in-context learning (ICL) and even zero-shot learning capabilities to solve downstream tasks without specifically designed supervised fine-tuning. In this paper, we propose utilizing LLMs for geoscience literature information extraction. Specifically, we design a hierarchical PDF parsing pipeline and an automated knowledge extraction process, which can significantly reduce the need for manual data annotation, assisting geoscientists in literature data mining. For the hierarchical PDF parsing pipeline, firstly, a document layout detection model fine-tuned on geoscience literature is employed for layout detection, obtaining layout detection information for the document. Secondly, based on the document layout information, an optical character content parsing model is used for content parsing, obtaining the text structure and plain text corresponding to the content. Finally, the text structure and plain text are combined and reconstructed to ultimately obtain the parsed structured data. For the automated knowledge extraction process, firstly, the parsed long text is segmented into paragraphs to adapt to the input length limit of LLMs. Subsequently, a few-shot prompting method is employed for structured knowledge extraction, encompassing two tasks: attribute value extraction and triplet extraction. In attribute value extraction, prompts are generated automatically by the LLMs based on the subdomain and attribute names, facilitating the location and extraction of values related to subdomain attribute names in the text. For triplet extraction, the LLMs employ a procedural approach to entity extraction, entity type extraction, and relation extraction, following the knowledge graph structure pattern. Finally, the extracted structured knowledge is stored in the form of knowledge graphs, facilitating further analysis and integration of various types of knowledge from the literature. Our proposed approach turns out to be simple, flexible, and highly effective in geoscience literature information extraction. Demonstrations of information extraction in subdomains such as radiolarian fossils and fluvial facies have yielded satisfactory results. The extraction efficiency has significantly improved, and feedback from domain experts indicates a relatively high level of accuracy in the extraction process. The extracted results can be used to construct a foundational knowledge graph for geoscience literature, supporting the comprehensive construction and efficient application of a geoscience knowledge graph.

This landscape study aims to provide an understanding of Large Language Models (LLMs), especially with a view point of supporting scientific and community queries for climate resilience and preparedness. Typically, for queries related to climate resilience and preparedness, the data span multiple heterogeneous sources and are complex by nature. Scientists as well as communities seek answers to real-world questions from LLMs, yet the accuracy of the feedback is not always guaranteed to be consistent and free of hallucinations. Given the complex landscape and the number of LLM models available, the choice of a model becomes complex too. In addition, LLM ensemble models are also taking on an important role where high level of trustworthiness and accuracy is needed. To address this gap, we performed a review of the LLM research landscape, identifying common themes. This was followed by a deep dive into ensemble models. We evaluate the ensembles as well as a popular single LLM model (that is, ChatGPT) with two sample queries: (i) ‘Are there any linkages between sea ice retreat and ice shelf melt in the Antarctic?’, (ii) ‘What is the best crop for sandy soils?’. The responses were assessed for robustness and accuracy by the domain expert. Through our analysis we concluded that a single LLM provides a parameter free setup whereas the ensemble models needed fine tuning to arrive to robust outcomes. However, the paper does not address ensemble performance issues and neither does it diminish their importance. Instead, this indicates that a lot more research is needed to get ensembles to a more user-friendly and approachable state of use unlike single LLMs. We also outline criteria that an ensemble model selection will need to consider such as initial model selection, retraining, ensemble optimization, energy utilization.

Large Language Models (LLMs) have emerged as a promising alternative to traditional static program analysis methods, such as symbolic execution, offering the ability to reason over code directly without relying on theorem provers or SMT solvers. However, LLMs are also inherently approximate by nature, and therefore face significant challenges in relation to the accuracy and scale of analysis in real-world applications. Such issues often necessitate the use of larger LLMs with higher token limits, but this requires enterprise-grade hardware (GPUs) and thus limits accessibility for many users. In this paper, we propose LLM-based symbolic execution —a novel approach that enhances LLM inference via a path-based decomposition of the program analysis tasks into smaller (more tractable) subtasks. The core idea is to generalize path constraints using a generic code-based representation that the LLM can directly reason over, and without translation into another (less-expressive) formal language. We implement our approach in the form of AutoBug, an LLM-based symbolic execution engine that is lightweight and language-agnostic, making it a practical tool for analyzing code that is challenging for traditional approaches. We show that AutoBug can improve both the accuracy and scale of LLM-based program analysis, especially for smaller LLMs that can run on consumer-grade hardware.

Large Language Models (LLMs) have become integral to a wide spectrum of applications, ranging from traditional computing tasks to advanced artificial intelligence (AI) applications. This widespread adoption has spurred extensive research into LLMs across various disciplines, including the social sciences. Notably, studies have revealed that LLMs possess emotional intelligence, which can be further developed through positive emotional stimuli. This discovery raises an intriguing question: can negative emotions similarly influence LLMs, potentially enhancing their performance? In response to this question, we introduce NegativePrompt, a novel approach underpinned by psychological principles, involving ten specifically designed negative emotional stimuli. We embark on rigorous experimental evaluations of five LLMs including Flan-T5-Large, Vicuna, Llama 2, ChatGPT, and GPT-4, across a set of 45 tasks. The results are revealing: NegativePrompt markedly enhances the performance of LLMs, evidenced by relative improvements of 12.89% in Instruction Induction tasks and 46.25% in BIG-Bench tasks. Moreover, we conduct attention visualization experiments to decipher the underlying mechanisms of NegativePrompt's influence. Our research contributes significantly to the understanding of LLMs and emotion interaction, demonstrating the practical efficacy of NegativePrompt as an emotion-driven method and offering novel insights for the enhancement of LLMs in real-world applications. The code is available at https://github.com/wangxu0820/NegativePrompt.

This study investigates the behaviors of Large Language Models (LLMs) when faced with conflicting prompts versus their internal memory. This will not only help to understand LLMs' decision mechanism but also benefit real-world applications, such as retrievalaugmented generation (RAG). Drawing on cognitive theory, we target the first scenario of decision-making styles where there is no superiority in the conflict and categorize LLMs' preference into dependent, intuitive, and rational/irrational styles. Another scenario of factual robustness considers the correctness of prompt and memory in knowledge-intensive tasks, which can also distinguish if LLMs behave rationally or irrationally in the first scenario. To quantify them, we establish a complete benchmarking framework including a dataset, a robustness evaluation pipeline, and corresponding metrics. Extensive experiments with seven LLMs reveal their varying behaviors. And, with role play intervention, we can change the styles, but different models present distinct adaptivity and upper-bound. One of our key takeaways is to optimize models or the prompts according to the identified style. For instance, RAG models with high role play adaptability may dynamically adjust the interventions according to the quality of retrieval results -being dependent to better leverage informative context; and, being intuitive when external prompt is noisy.

Despite being empowered with alignment mechanisms, large language models (LLMs) are increasingly vulnerable to emerging jailbreak attacks that can compromise their alignment mechanisms. This vulnerability poses significant risks to real-world applications. Existing work faces challenges in both training efficiency and generalization capabilities (i.e., Reinforcement Learning from Human Feedback and Red-Teaming). Developing effective strategies to enable LLMs to resist continuously evolving jailbreak attempts represents a significant challenge. To address this challenge, we propose a novel defensive paradigm called GuidelineLLM, which assists LLMs in recognizing queries that may have harmful content. Before LLMs respond to a query, GuidelineLLM first identifies potential risks associated with the query, summarizes these risks into guideline suggestions, and then feeds these guidelines to the responding LLMs. Importantly, our approach eliminates the necessity for additional safety fine-tuning of the LLMs themselves; only the GuidelineLLM requires fine-tuning. This characteristic enhances the general applicability of GuidelineLLM across various LLMs. Experimental results demonstrate that GuidelineLLM can significantly reduce the attack success rate (ASR) against LLM (an average reduction of 34.17% ASR) while maintaining the usefulness of LLM in handling benign queries.

Students must navigate large catalogs of courses and make appropriate enrollment decisions in many online learning environments. In this context, identifying key concepts and their relationships is essential for understanding course content and informing course recommendations. However, identifying and extracting concepts can be an extremely labor-intensive and time-consuming task when it has to be done manually. Traditional NLP-based methods to extract relevant concepts from courses heavily rely on resource-intensive preparation of detailed course materials, thereby failing to minimize labor. As recent advances in large language models (LLMs) offer a promising alternative for automating concept identification and relationship inference, we thoroughly investigate the potential of LLMs in automatically generating course concepts and their relations. Specifically, we systematically evaluate three LLM variants (GPT-3.5, GPT-4o-mini, and GPT-4o) across three distinct educational tasks, which are concept generation, concept extraction, and relation identification, using six systematically designed prompt configurations that range from minimal context (course title only) to rich context (course description, seed concepts, and subtitles). We systematically assess model performance through extensive automated experiments using standard metrics (Precision, Recall, F1, and Accuracy) and human evaluation by four domain experts, providing a comprehensive analysis of how prompt design and model choice influence the quality and reliability of the generated concepts and their interrelations. Our results show that GPT-3.5 achieves the highest scores on quantitative metrics, whereas GPT-4o and GPT-4o-mini often generate concepts that are more educationally meaningful despite lexical divergence from the ground truth. Nevertheless, LLM outputs still require expert revision, and performance is sensitive to prompt complexity. Overall, our experiments demonstrate the viability of LLMs as a tool for supporting educational content selection and delivery.

BackgroundDisease name recognition is a fundamental task in clinical natural language processing, enabling the extraction of critical patient information from electronic health records. While recent advances in large language models (LLMs) have shown promise, most evaluations have focused on English, and little is known about their robustness in low-resource languages such as Japanese. In particular, whether these models can perform reliably on previously unseen in-hospital data, which differs from training data in writing styles and clinical contexts, has not been thoroughly investigated.ObjectiveThis study evaluated the robustness of fine-tuned LLMs for disease name recognition in Japanese clinical notes, with a particular focus on their performance on in-hospital data that was not included during training.MethodsWe used two corpora for this study: (1) a publicly available set of Japanese case reports denoted as CR, and (2) a newly constructed corpus of progress notes, denoted as PN, written by ten physicians to capture stylistic variations of in-hospital clinical notes. To reflect real-world deployment scenarios, we first fine-tuned models on CR. Specifically, we compared a LLM and a baseline-masked language model (MLM). These models were then evaluated under two conditions: (1) on CR, representing the in-domain (ID) setting with the same document type, similar to training, and (2) on PN, representing the out-of-domain (OOD) setting with a different document type. Robustness was assessed by calculating the performance gap (ie, the performance drop from in-domain to out-of-domain settings).ResultsThe LLM demonstrated greater robustness, with a smaller performance gap in F1-scores (ID–OOD = −8.6) compared to the MLM baseline performance (ID–OOD = −13.9). This indicated more stable performance across ID and OOD settings, highlighting the effectiveness of fine-tuned LLMs for reliable use in diverse clinical settings.ConclusionsFine-tuned LLMs demonstrate superior robustness for disease name recognition in Japanese clinical notes, with a smaller performance gap. These findings highlight the potential of LLMs as reliable tools for clinical natural language processing in low-resource language settings and support their deployment in real-world health care applications, where diversity in documentation is inevitable.

Entity Resolution (ER) is the problem of semi-automatically determining when two entities refer to the same underlying entity, with applications ranging from healthcare to e-commerce. Traditional ER solutions required considerable manual expertise, including domain-specific feature engineering, as well as identification and curation of training data. Recently released large language models (LLMs) provide an opportunity to make ER more seamless and domain-independent. Because of LLMs’ pre-trained knowledge, the matching step in ER can be made easier by just prompting. However, it is also well known that LLMs can pose risks, that the quality of their outputs can depend on how prompts are engineered, and that the cost of using LLMs can be significant. Unfortunately, a systematic experimental study on the effects of different prompting methods and their respective cost for solving domain-specific entity matching using LLMs, like ChatGPT, has been lacking thus far. This paper aims to address this gap by conducting such a study. We consider some relatively simple and cost-efficient ER prompt engineering methods and apply them to perform product matching on two real-world datasets widely used in the community. We select two well-known e-commerce datasets and provide extensive experimental results to show that an LLM like GPT3.5 is viable for high-performing product matching and, interestingly, that more complicated and detailed (and hence, expensive) prompting methods do not necessarily outperform simpler approaches. We provide brief discussions on qualitative and error analysis, including a study of the inter-consistency of different prompting methods to determine whether they yield stable outputs. Finally, we consider some limitations of LLMs when used as a product matcher in potential real-world e-commerce applications.

Graphs are a powerful tool for representing and analyzing complex relationships in real-world applications. Large Language Models (LLMs) have demonstrated impressive capabilities by advancing state-of-the-art on many language-based benchmarks. Their ability to process and understand natural language open exciting possibilities in various domains. Despite the remarkable progress in automated reasoning with natural text, reasoning on graphs with LLMs remains an understudied problem that has recently gained more attention.This tutorial builds upon recent advances in expressing reasoning problems through the lens of tasks on graph data. The first part of the tutorial will provide an in-depth discussion of techniques for representing graphs as inputs to LLMs. The second, hands-on, portion will demonstrate these techniques in a practical setting. As a learning outcome of participating in the tutorial, participants will be able to analyze graphs either on free-tier Colab or their local machines with the help of LLMs.

In this work, we are interested in automated methods for knowledge graph creation (KGC) from input text. Progress on large language models (LLMs) has prompted a series of recent works applying them to KGC, e.g., via zero/few-shot prompting. Despite successes on small domain-specific datasets, these models face difficulties scaling up to text common in many real-world applications. A principal issue is that, in prior methods, the KG schema has to be included in the LLM prompt to generate valid triplets; larger and more complex schemas easily exceed the LLMs' context window length. Furthermore, there are scenarios where a fixed pre-defined schema is not available and we would like the method to construct a high-quality KG with a succinct selfgenerated schema. To address these problems, we propose a three-phase framework named Extract-Define-Canonicalize (EDC): open information extraction followed by schema definition and post-hoc canonicalization. EDC is flexible in that it can be applied to settings where a pre-defined target schema is available and when it is not; in the latter case, it constructs a schema automatically and applies selfcanonicalization. To further improve performance, we introduce a trained component that retrieves schema elements relevant to the input text; this improves the LLMs' extraction performance in a retrieval-augmented generationlike manner. We demonstrate on three KGC benchmarks that EDC is able to extract highquality triplets without any parameter tuning and with significantly larger schemas compared to prior works. Code for EDC is available at https://github.com/clear-nus/edc.

Large language models (LLMs) are rapidly advancing natural language processing and driving increasing interest across biomedical research, clinical care, and healthcare operations. This systematic review synthesizes current empirical evidence on LLM applications in healthcare and biomedical informatics, focusing on their capabilities, evaluation practices, and reported outcomes. Existing studies highlight promising uses in research, where LLMs assist literature-informed genomic interpretation, functional annotation, and biological hypothesis generation, as well as support tasks related to protein and multiomics analysis. In clinical contexts, LLMs are primarily evaluated for natural language-driven tasks, including electronic health record summarization, clinical documentation support, medical question answering, and information extraction, rather than autonomous diagnostic or therapeutic decision-making. Early investigations also describe potential value in healthcare operations, patient communication, clinician education, and drug discovery workflows largely through knowledge retrieval, text generation, and semantic search. However, current evidence remains preliminary: most studies are retrospective, benchmark-based, simulation-driven, or limited to controlled research settings. Key challenges include hallucination and unreliable reasoning, bias and inequitable performance across populations, data privacy and security constraints, reproducibility limitations, and lack of prospective clinical validation and regulatory guidance. Emerging strategies, such as domain-specific pretraining, retrieval augmentation, multi-modal architectures, and privacy-preserving learning, aim to improve reliability, safety, and real-world applicability. This review concludes by outlining methodological, infrastructural, and governance requirements needed to responsibly integrate LLMs into biomedical workflows, emphasizing that clinical deployment remains exploratory and must be rigorously evaluated.