Prompt optimization aims to search for effective prompts that enhance the performance of large language models (LLMs). Although existing prompt optimization methods have discovered effective prompts, they often differ from sophisticated prompts carefully designed by human experts. Prompt design strategies, representing best practices for improving prompt performance, can be key to improving prompt optimization. Recently, a method termed the Autonomous Prompt Engineering Toolbox (APET) has incorporated various prompt design strategies into the prompt optimization process. In APET, the LLM is needed to implicitly select and apply the appropriate strategies because prompt design strategies can have negative effects. This implicit selection may be suboptimal due to the limited optimization capabilities of LLMs. This paper introduces Optimizing Prompts with sTrategy Selection (OPTS), which implements explicit selection mechanisms for prompt design. We propose three mechanisms, including a Thompson sampling-based approach, and integrate them into EvoPrompt, a well-known prompt optimizer. Experiments optimizing prompts for two LLMs, Llama-3-8B-Instruct and GPT-4o mini, were conducted using BIG-Bench Hard. Our results show that the selection of prompt design strategies improves the performance of EvoPrompt, and the Thompson sampling-based mechanism achieves the best overall results. Our experimental code is provided at https://github.com/shiralab/OPTS .

Large Language Models (LLMs) have fundamentally transformed approaches to Natural Language Processing (NLP) tasks across diverse domains. In healthcare, accurate and cost-efficient text classification is crucial, whether for clinical notes analysis, diagnosis coding, or any other task, and LLMs present promising potential. Text classification has always faced multiple challenges, including manual annotation for training, handling imbalanced data, and developing scalable approaches. With healthcare, additional challenges are added, particularly the critical need to preserve patients' data privacy and the complexity of the medical terminology. Numerous studies have been conducted to leverage LLMs for automated healthcare text classification and contrast the results with existing machine learning-based methods where embedding, annotation, and training are traditionally required. Existing systematic reviews about LLMs either do not specialize in text classification or do not focus on the healthcare domain. This research synthesizes and critically evaluates the current evidence found in the literature regarding the use of LLMs for text classification in a healthcare setting. Major databases (e.g., Google Scholar, Scopus, PubMed, Science Direct) and other resources were queried, which focused on the papers published between 2018 and 2024 within the framework of PRISMA guidelines, which resulted in 65 eligible research articles. These were categorized by text classification type (e.g., binary classification, multi-label classification), application (e.g., clinical decision support, public health and opinion analysis), methodology, type of healthcare text, and metrics used for evaluation and validation. This review reveals the existing gaps in the literature and suggests future research lines that can be investigated and explored.

The rise of foundation models has revolutionized natural language processing and computer vision, yet their best practices to time series forecasting remains underexplored. Existing time series foundation models often adopt methodologies from these fields without addressing the unique characteristics of time series data. In this paper, we identify two key challenges in cross-domain time series forecasting: the complexity of temporal patterns and semantic misalignment. To tackle these issues, we propose the ``Unify and Anchor" transfer paradigm, which disentangles frequency components for a unified perspective and incorporates external context as domain anchors for guided adaptation. Based on this framework, we introduce ContexTST, a Transformer-based model that employs a time series coordinator for structured representation and the Transformer blocks with a context-informed mixture-of-experts mechanism for effective cross-domain generalization. Extensive experiments demonstrate that ContexTST advances state-of-the-art forecasting performance while achieving strong zero-shot transferability across diverse domains.

We present ReaderLM-v2, a compact 1.5 billion parameter language model designed for efficient web content extraction. Our model processes documents up to 512K tokens, transforming messy HTML into clean Markdown or JSON formats with high accuracy -- making it an ideal tool for grounding large language models. The model's effectiveness results from two key innovations: (1) a three-stage data synthesis pipeline that generates high quality, diverse training data by iteratively drafting, refining, and critiquing web content extraction; and (2) a unified training framework combining continuous pre-training with multi-objective optimization. Intensive evaluation demonstrates that ReaderLM-v2 outperforms GPT-4o-2024-08-06 and other larger models by 15-20\% on carefully curated benchmarks, particularly excelling at documents exceeding 100K tokens, while maintaining significantly lower computational requirements.

Large language models (LLMs) excel in high-resource languages but struggle with low-resource languages (LRLs), particularly those spoken by minority communities in China, such as Tibetan, Uyghur, Kazakh, and Mongolian. To systematically track the progress in these languages, we introduce MiLiC-Eval, a benchmark designed for minority languages in China, featuring 24K instances across 9 tasks. MiLiC-Eval focuses on underrepresented writing systems and provides a fine-grained assessment of linguistic and problem-solving skills. Our evaluation reveals that LLMs perform poorly on syntax-intensive tasks and multi-script languages. We further demonstrate how MiLiC-Eval can help advance LRL research in handling diverse writing systems and understanding the process of language adaptation.

Chain-of-thought prompting has emerged as a powerful technique for enabling large language models (LLMs) to solve complex reasoning tasks. However, these reasoning chains can be verbose, raising concerns about efficiency. In response, recent works have sought to decrease response lengths through simple prompting strategies (e.g. 'be concise'). In this work, we conduct the first systematic study of the relationship between reasoning length and model performance across a diverse range of compression instructions (e.g. 'use 10 words or less' or 'remove all punctuation'). In doing so, we discover a universal tradeoff between reasoning length and accuracy that persists across even very distinct reasoning chains. We demonstrate that this tradeoff emerges from a sharp threshold behavior at the question level: each task has an intrinsic 'token complexity' - a minimal number of tokens required for successful problem-solving. We show how token complexity enables us to compute information-theoretic limits on the accuracy-compression tradeoff, and find that prompt-based compression strategies operate far from these theoretical limits. This suggests there may be significant room for improvement and our framework provides a benchmark to help researchers evaluate progress in reasoning efficiency. Our work also highlights the importance of adaptive compression -- giving shorter responses for easier questions -- and we show that token complexity is a useful tool for measuring this capability.

This paper presents an extensive examination of Parameter-Efficient Fine-Tuning (PEFT) for embedding domain specific facts into Large Language Models (LLMs), focusing on improving the fine-tuning process by categorizing question-answer (QA) pairs into Factual and Conceptual classes using a BERT-based classifier. Two distinct Llama-2 models are fine-tuned based on these classifications and evaluated using larger models like GPT-3.5 Turbo and Gemini. Our results indicate that models trained on conceptual datasets outperform those trained on factual datasets. Additionally, we compare the efficiency of two synthetic fine-tuning dataset generation techniques, D-RAG and D-Naive, with D-Naive demonstrating superior performance. Although PEFT has shown effectiveness, our research indicates that it may not be the most optimal method for embedding facts into LLMs. However, it has demonstrated exceptional performance in instruction-based tasks. Our findings are reinforced by a 1000-sample dataset in the data center domain, where the fine-tuned Llama-2 7B model significantly outperforms the baseline model in generating product recommendations. Our study highlights the importance of QA pair categorization and synthetic dataset generation techniques in enhancing the performance of LLMs in specific domains.

Smart contracts are crucial programs on blockchains, and their immutability post-deployment makes functional correctness vital. Despite progress in code completion models, benchmarks for Solidity, the primary smart contract language, are lacking. Existing metrics like BLEU do not adequately assess the functional correctness of generated smart contracts. To fill this gap, we introduce SolBench, a benchmark for evaluating the functional correctness of Solidity smart contracts generated by code completion models. SolBench includes 4,178 functions from 1,155 Ethereum-deployed contracts. Testing advanced models revealed challenges in generating correct code without context, as Solidity functions rely on context-defined variables and interfaces. To address this, we propose a Retrieval-Augmented Code Repair framework. In this framework, an executor verifies functional correctness, and if necessary, an LLM repairs the code using retrieved snippets informed by executor traces. We conduct a comprehensive evaluation of both closed-source and open-source LLMs across various model sizes and series to assess their performance in smart contract completion. The results show that code repair and retrieval techniques effectively enhance the correctness of smart contract completion while reducing computational costs.

Language-Guided Object Search in Agricultural Environments Advaith Balaji 1, Saket Pradhan 1, Dmitry Berenson 1 Abstract -- Creating robots that can assist in farms and gardens can help reduce the mental and physical workload experienced by farm workers. We tackle the problem of object search in a farm environment, providing a method that allows a robot to semantically reason about the location of an unseen target object among a set of previously seen objects in the environment using a Large Language Model (LLM). We leverage object-to-object semantic relationships to plan a path through the environment that will allow us to accurately and efficiently locate our target object while also reducing the overall distance traveled, without needing high-level room or area-level semantic relationships. During our evaluations, we found that our method outperformed a current state-of-the-art baseline and our ablations. Our offline testing yielded an average path efficiency of 84%, reflecting how closely the predicted path aligns with the ideal path. Upon deploying our system on the Boston Dynamics Spot robot in a real-world farm environment, we found that our system had a success rate of 80%, with a success weighted by path length of 0.67, which demonstrates a reasonable trade-off between task success and path efficiency under real-world conditions. The project website can be viewed at: adi-balaji.github.io/losae I. INTRODUCTION Multiple studies investigating the stress experienced by farmers reported that the combination of the high workload and physical effort resulted in considerable levels of fatigue and mental strain [1], [2]. Studies have also found that increasing mechanization and the use of automated machinery relatively reduces the workload experienced by farmers [3]. Integrating robots into current farm environments can further reduce the workload experienced by farmers.

From a first-principles perspective, it may seem odd that the strongest results in foundation model fine-tuning (FT) are achieved via a relatively complex, two-stage training procedure. Specifically, one first trains a reward model (RM) on some dataset (e.g. human preferences) before using it to provide online feedback as part of a downstream reinforcement learning (RL) procedure, rather than directly optimizing the policy parameters on the dataset via offline maximum likelihood estimation. In fact, from an information-theoretic perspective, we can only lose information via passing through a reward model and cannot create any new information via on-policy sampling. To explain this discrepancy, we scrutinize several hypotheses on the value of RL in FT through both theoretical and empirical lenses. Of the hypotheses considered, we find the most support for the explanation that on problems with a generation-verification gap, the combination of the ease of learning the relatively simple RM (verifier) from the preference data, coupled with the ability of the downstream RL procedure to then filter its search space to the subset of policies (generators) that are optimal for relatively simple verifiers is what leads to the superior performance of online FT.