Related papers: How Many Tries Does It Take? Iterative Self-Repair…

Large language models with billions of parameters, such as GPT-3.5, GPT-4, and LLaMA, are increasingly prevalent. Numerous studies have explored effective prompting techniques to harness the power of these LLMs for various research…

Large Language Models (LLMs) have revolutionized code generation but require significant resources and often over-generalize, limiting their task-specific efficiency. Fine-tuning smaller, open-source LLMs provides a cost-effective…

Strategic model selection and reasoning settings are more effective than ensembling for optimizing automated scoring with large language models (LLMs). We examined self-consistency (intra-model majority voting) and reasoning effort for…

With LLM usage becoming widespread across countries, languages, and humanity more broadly, the need to understand and guardrail their multilingual responses increases. Large-scale datasets for testing and benchmarking have been created to…

Despite the great advance of Multimodal Large Language Models (MLLMs) in both instruction dataset building and benchmarking, the independence of training and evaluation makes current MLLMs hard to further improve their capability under the…

This study investigates whether repeating questions within prompts influences the performance of large language models (LLMs). We hypothesize that reiterating a question within a single prompt might enhance the model's focus on key elements…

Intrinsic self-correction was proposed to improve LLMs' responses via feedback prompts solely based on their inherent capability. However, recent works show that LLMs' intrinsic self-correction fails without oracle labels as feedback…

Leading large language models have demonstrated impressive capabilities in reasoning-intensive tasks, such as standardized educational testing. However, they often require extensive training in low-resource settings with inaccessible…

Generating high-quality code that solves complex programming tasks is challenging, especially with current decoder-based models that produce highly stochastic outputs. In code generation, even minor errors can easily break the entire…

Bug reports contain the information developers need to triage and fix software bugs. However, unclear, incomplete, or ambiguous information may lead to delays and excessive manual effort spent on bug triage and resolution. In this paper, we…

LLM-based automated program repair methods have attracted significant attention for their state-of-the-art performance. However, they were primarily evaluated on a few well known datasets like Defects4J, raising questions about their…

The self-improving ability of large language models (LLMs), enabled by prompting them to analyze and revise their own outputs, has garnered significant interest in recent research. However, this ability has been shown to be absent and…

Using Large Language Models (LLMs) to produce robot programs from natural language has allowed for robot systems that can complete a higher diversity of tasks. However, LLM-generated programs may be faulty, either due to ambiguity in…

We evaluated 4 systems (ELIZA, GPT-4o, LLaMa-3.1-405B, and GPT-4.5) in two randomised, controlled, and pre-registered Turing tests on independent populations. Participants had 5 minute conversations simultaneously with another human…

Large language models (LLMs) are increasingly embedded in AI-based tutoring systems. Can they faithfully model novice reasoning and metacognitive judgments? Existing evaluations emphasize problem-solving accuracy, overlooking the fragmented…

Qualitative analysis plays a pivotal role in understanding the human and social aspects of software engineering. However, it remains a demanding process shaped by the subjective interpretation of individual researchers and sensitive to…

Various techniques have been proposed to improve large language models (LLMs) adherence to formatting and instruction constraints. One of the most effective approaches involves utilizing high-quality data generated by powerful models.…

Language models such as GPT and Llama have shown remarkable ability on diverse natural language tasks, yet their performance on complex table tasks (e.g., NL-to-Code and data cleaning) remains suboptimal. Improving performance typically…

The automatic generation of hints by Large Language Models (LLMs) within Intelligent Tutoring Systems (ITSs) has shown potential to enhance student learning. However, generating pedagogically sound hints that address student misconceptions…

The synthesis of inductive loop invariants is a critical bottleneck in automated program verification. While Large Language Models (LLMs) show promise in mitigating this issue, they often fail on hard instances, generating invariants that…