Related papers: ReflectionCoder: Learning from Reflection Sequence…
Generating with citations is crucial for trustworthy Large Language Models (LLMs), yet even advanced LLMs often produce mismatched or irrelevant citations. Existing methods over-optimize citation fidelity while overlooking relevance to the…
Generative Recommendation (GR) has become a promising paradigm for large-scale recommendation systems. However, existing GR models typically perform single-pass decoding without explicit refinement, causing early deviations to accumulate…
We examine whether data generated by explanation techniques, which promote a process of self-reflection, can improve classifier performance. Our work is based on the idea that humans have the ability to make quick, intuitive decisions as…
Recent advancements in language modeling have enabled the translation of natural language into code, and the use of execution feedback to improve code generation. However, these methods often rely heavily on pre-existing test cases, which…
Reproducing buggy code is the first and crucially important step in issue resolving, as it aids in identifying the underlying problems and validating that generated patches resolve the problem. While numerous approaches have been proposed…
Despite the remarkable capabilities of large language models (LLMs) in natural language understanding and reasoning, they often display undesirable behaviors, such as generating hallucinations and unfaithful reasoning. A prevalent strategy…
Reflection in Kotlin is a powerful mechanism to introspect program behavior during its execution at run-time. However, among the variety of practical tasks involving reflection, there are scenarios when the poor performance of run-time…
In real-world software engineering tasks, solving a problem often requires understanding and modifying multiple functions, classes, and files across a large codebase. Therefore, on the repository level, it is crucial to extract the relevant…
We present a novel pipeline, ReflectEvo, to demonstrate that small language models (SLMs) can enhance meta introspection through reflection learning. This process iteratively generates self-reflection for self-training, fostering a…
Recent advancements in Large Language Models (LLMs) have expanded the horizons of natural language understanding and generation. Notably, the output control and alignment with the input of LLMs can be refined through instruction tuning.…
The escalating complexity of modern codebases has intensified the need for retrieval systems capable of interpreting cross-component change intents, a capability fundamentally absent in conventional function-level search paradigms. While…
We explore a method for improving the performance of large language models through self-reflection and reinforcement learning. By incentivizing the model to generate better self-reflections when it answers incorrectly, we demonstrate that a…
Pre-trained code language models have achieved promising performance in code generation and improved the programming efficiency of human developers. However, their self-refinement capability is typically overlooked by the existing…
Large reasoning models (LRMs), such as OpenAI's o1 and DeepSeek-R1, harness test-time scaling to perform multi-step reasoning for complex problem-solving. This reasoning process, executed before producing final answers, is often guided by…
Large Language Models (LLMs) have recently made significant advances in code generation through the 'Chain-of-Thought' prompting technique. This technique empowers the model to autonomously devise "solution plans" to tackle intricate…
Recent text-to-image diffusion models achieve impressive visual quality through extensive scaling of training data and model parameters, yet they often struggle with complex scenes and fine-grained details. Inspired by the self-reflection…
Code generation tasks aim to automate the conversion of user requirements into executable code, significantly reducing manual development efforts and enhancing software productivity. The emergence of large language models (LLMs) has…
Recently, large language models (LLMs) have achieved significant progress in automated code generation. Despite their strong instruction-following capabilities, these models frequently struggled to align with user intent in coding…
Automated code generation remains a persistent challenge in software engineering, as conventional multi-agent frameworks are often constrained by static planning, isolated execution, high computational overhead, and limited adaptability to…
Repository-level code generation has attracted growing attention in recent years. Unlike function-level code generation, it requires the model to understand the entire repository, reasoning over complex dependencies across functions,…