Related papers: Defective Task Descriptions in LLM-Based Code Gene…

Vertical text input is commonly encountered in various real-world applications, such as mathematical computations and word-based Sudoku puzzles. While current large language models (LLMs) have excelled in natural language tasks, they remain…

Large language models (LLMs) often appear to excel on public benchmarks, but these high scores may mask an overreliance on dataset-specific surface cues rather than true language understanding. We introduce the Chameleon Benchmark Overfit…

Large Language Models (LLMs) have transformed code completion tasks, providing context-based suggestions to boost developer productivity in software engineering. As users often fine-tune these models for specific applications, poisoning and…

Reliably detecting when a deployed machine learning model is likely to fail on a given input is crucial for ensuring safe operation. In this work, we propose DECIDER (Debiasing Classifiers to Identify Errors Reliably), a novel approach that…

Text-based visual descriptors--ranging from simple class names to more descriptive phrases--are widely used in visual concept discovery and image classification with vision-language models (VLMs). Their effectiveness, however, depends on a…

Large Vision Language Models (LVLMs) have shown remarkable capabilities in multimodal tasks like visual question answering or image captioning. However, inconsistencies between the visual information and the generated text, a phenomenon…

Large Language Models (LLMs) have become powerful tools for automated code generation. However, these models often overlook critical security practices, which can result in the generation of insecure code that contains…

This paper presents insights from evaluating 16 frontier large language models (LLMs) on the WebApp1K benchmark, a test suite designed to assess the ability of LLMs to generate web application code. The results reveal that while all models…

Verification is becoming central to both reinforcement-learning-based training and inference-time control of large language models (LLMs). Yet current verifiers face a fundamental trade-off: LLM-based verifiers are expressive but hard to…

Solving problems through tool use under explicit constraints constitutes a highly challenging yet unavoidable scenario for large language models (LLMs), requiring capabilities such as function calling, instruction following, and…

We present AutoBencher, a declarative framework for automatic benchmark construction, and use it to scalably discover novel insights and vulnerabilities of existing language models. Concretely, given a few desiderata of benchmarks (e.g.,…

$ $Large Language Models (LLMs) are being increasingly utilized in various applications, with code generations being a notable example. While previous research has shown that LLMs have the capability to generate both secure and insecure…

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…

Large language models (LLMs) have demonstrated remarkable capabilities in code generation tasks. However, repository-level code generation presents unique challenges, particularly due to the need to utilize information spread across…

Although large language models (LLMs) have become more capable and accurate across many tasks, some fundamental sources of unreliability remain in their behavior. One key limitation is their inconsistency at reporting the same information…

Modern software relies on a multitude of automated testing and quality assurance tools to prevent errors, bugs and potential vulnerabilities. This study sets out to provide a head-to-head, quantitative and qualitative evaluation of six…

Large language models (LLMs) like GitHub Copilot and ChatGPT have emerged as powerful tools for code generation, significantly enhancing productivity and accelerating software development. However, existing benchmarks primarily focus on…

Modern generative pre-trained language models excel at open-ended text generation, yet continue to underperform on structure-related tasks such as NER, relation extraction, and semantic role labeling, especially when compared to…

Large language models (LLMs) such as GPT, Claude, Gemini, and Grok have been deeply integrated into our daily life. They now support a wide range of tasks -- from dialogue and email drafting to assisting with teaching and coding, serving as…

LLMs demonstrate significant potential across various software engineering tasks. However, they still face challenges in generating correct code on the first attempt when addressing complex requirements. Introducing a discriminator to…