Related papers: Rationale Dataset and Analysis for the Commit Mess…
Nonsensical and anomalous sentences have been instrumental in the development of computational models of semantic interpretation. A core challenge is to distinguish between what is merely anomalous (but can be interpreted given a supporting…
Large language models increasingly rely on explicit chain-of-thought reasoning to solve complex tasks, yet the safety of the reasoning process itself remains largely unaddressed. Existing work focuses predominantly on content safety (i.e.,…
Commit messages are explanations of changes made to a codebase that are stored in version control systems. They help developers understand the codebase as it evolves. However, writing commit messages can be tedious and inconsistent among…
The task of rationalization aims to extract pieces of input text as rationales to justify neural network predictions on text classification tasks. By definition, rationales represent key text pieces used for prediction and thus should have…
Large Language Models (LLMs) increasingly show reasoning rationales alongside their answers, turning "reasoning" into a user-interface element. While step-by-step rationales are typically associated with model performance, how they…
Code data has been shown to enhance the reasoning capabilities of large language models (LLMs), but it remains unclear which aspects of code are most responsible. We investigate this question with a systematic, data-centric framework. We…
Understanding and reasoning about code semantics is essential for enhancing code LLMs' abilities to solve real-world software engineering (SE) tasks. Although several code reasoning benchmarks exist, most rely on synthetic datasets or…
The development of large language models (LLM) has shown progress on reasoning, though studies have largely considered either English or simple reasoning tasks. To address this, we introduce a multilingual structured reasoning and…
Commit messages are important for software development and maintenance. Many neural network-based approaches have been proposed and shown promising results on automatic commit message generation. However, the generated commit messages could…
Large Reasoning Models (LRMs) are often bottlenecked by the high cost of output tokens. We show that a significant portion of these tokens are useless self-repetitions - what we call "word salad" - that exhaust the decoding budget without…
Reasoning in Large Language Models (LLMs) poses a challenge for oversight as many misaligned behaviors do not surface until reasoning concludes. To address this, we introduce Behavior Cue Reasoning for making LLM reasoning more controllable…
ICD coding is the process of mapping unstructured text from Electronic Health Records (EHRs) to standardised codes defined by the International Classification of Diseases (ICD) system. In order to promote trust and transparency, existing…
The widespread adoption of open-source ecosystems enables developers to integrate third-party packages, but also exposes them to malicious packages crafted to execute harmful behavior via public repositories such as PyPI. Existing datasets…
Training Large Language Models (LLMs) for chain-of-thought reasoning presents a significant challenge: supervised fine-tuning on a single "golden" rationale hurts generalization as it penalizes equally valid alternatives, whereas…
Controllers for structured LM reasoning (e.g., Chain-of-Thought, self-consistency, and Tree-of-Thoughts) often entangle what to try next with how to execute it, exposing only coarse global knobs and yielding brittle, compute-inefficient,…
With the release of R1, a publicly available large reasoning model (LRM), researchers commonly train new LRMs by training language models on R1's long chain-of-thought (CoT) inferences. While prior works show that LRMs' capabilities can be…
Commit messages are the atomic level of software documentation. They provide a natural language description of the code change and its purpose. Messages are critical for software maintenance and program comprehension. Unlike documenting…
Reasoning LLMs often spend substantial tokens on long intermediate reasoning traces (e.g., chain-of-thought) when solving new problems. We propose to summarize and store reusable reasoning skills distilled from extensive deliberation and…
A programming language is a formally constructed language designed to communicate instructions to a machine, particularly a computer. Programming languages can be used to create programs to control the behavior of a machine or to express…
Large language models (LLMs) can achieve strong reasoning performance with sufficient computation, but they do not inherently know how much computation a task requires. We study budgeted inference-time reasoning for multiple tasks under a…