相关论文: Specification Self-Correction: Mitigating In-Conte…

Specification mining offers a solution by automating security specification for hardware. Specification miners use a form of machine learning to specify behaviors of a system by studying a system in execution. However, specification mining…

Chinese Spell Checking (CSC) aims to detect and correct spelling errors in sentences. Despite Large Language Models (LLMs) exhibit robust capabilities and are widely applied in various tasks, their performance on CSC is often…

Large Language Models (LLMs) often exhibit strong linguistic abilities while remaining unreliable on multi-step reasoning tasks, particularly when deployed without additional training or fine-tuning. In this work, we study inference-time…

Large language models (LLMs) have exhibited remarkable ability in code generation. However, generating the correct solution in a single attempt still remains a challenge. Prior works utilize verification properties in software engineering…

Large language models have transformed natural language processing, yet supervised fine-tuning (SFT) remains computationally intensive. This paper formally proves that capabilities acquired through SFT can be approximated by a base…

Large Language Models (LLMs) are increasingly used in a variety of important applications, yet their safety and reliability remain as major concerns. Various adversarial and jailbreak attacks have been proposed to bypass the safety…

We introduce SELECT (Scene tExt Label Errors deteCTion), a novel approach that leverages multi-modal training to detect label errors in real-world scene text datasets. Utilizing an image-text encoder and a character-level tokenizer, SELECT…

Open-source Large Language Models (LLMs) often employ safety alignment methods to resist harmful instructions. However, recent research shows that maliciously fine-tuning these LLMs on harmful data can easily bypass these safeguards. To…

The risk of harmful content generated by large language models (LLMs) becomes a critical concern. This paper presents a systematic study on assessing and improving LLMs' capability to perform the task of \textbf{course-correction}, \ie, the…

Large language models (LLMs) can generate executable code from natural language descriptions, but the resulting programs frequently contain bugs due to hallucinations. In the absence of formal specifications, existing approaches attempt to…

Large language models (LLMs) are typically deployed with fixed parameters, and their performance is often improved by allocating more computation at inference time. While such test-time scaling can be effective, it cannot correct model…

Text-to-SQL systems translate natural language (NL) questions into SQL queries, enabling non-technical users to interact with structured data. While large language models (LLMs) have shown promising results on the text-to-SQL task, they…

Generations from large language models (LLMs) can be improved by sampling and scoring multiple solutions to select a final answer. Current "sample and select" methods such as self-consistency (SC) rely on majority voting to score answers.…

Large language models (LLMs) have opened new paradigms in optimization modeling by enabling the generation of executable solver code from natural language descriptions. Despite this promise, existing approaches typically remain…

Reinforcement learning (RL) has been widely adopted in post-training for large language models (LLMs) at scale. Recently, the incentivization of reasoning capabilities in LLMs from RL indicates that $\textit{proper learning methods could…

As Large Language Models (LLMs) scale in size and complexity, the consequences of failures during training become increasingly severe. A major challenge arises from Silent Data Corruption (SDC): hardware-induced faults that bypass…

Reinforcement learning for LLMs is vulnerable to reward hacking, where models exploit shortcuts to maximize reward without solving the intended task. We systematically study this phenomenon in coding tasks using an environment-manipulation…

A common paradigm to improve the performance of large language models is optimizing for a reward model. Reward models assign a numerical score to an LLM's output that indicates, for example, how likely it is to align with user preferences…

Structured product data, in the form of attribute-value pairs, is essential for e-commerce platforms to support features such as faceted product search and attribute-based product comparison. However, vendors often provide unstructured…

Self-correction in language models remains elusive. In this work, we explore whether language models can explicitly localize errors in incorrect reasoning, as a path toward building AI systems that can effectively correct themselves. We…