Related papers: Self-Correcting Code Generation Using Small Langua…

Can large language models improve without external data -- by generating their own questions and answers? We hypothesize that a pre-trained language model can improve its reasoning skills given only a single prompt specifying the topic…

AI assistance continues to help advance applications in education, from language learning to intelligent tutoring systems, yet current methods for providing students feedback are still quite limited. Most automatic feedback systems either…

Large Language Models (LLMs) exhibit remarkable generative capabilities, enabling the generation of valuable information. Despite these advancements, previous research found that LLMs sometimes struggle with adhering to specific constraints…

Large language models generate complex, open-ended outputs: instead of outputting a class label they write summaries, generate dialogue, or produce working code. In order to asses the reliability of these open-ended generation systems, we…

Developers often dedicate significant time to maintaining and refactoring existing code. However, most prior work on generative models for code focuses solely on creating new code, overlooking the distinctive needs of editing existing code.…

Large language models (LLMs) have achieved remarkable success across various natural language processing (NLP) tasks. However, recent studies suggest that they still face challenges in performing fundamental NLP tasks essential for deep…

Reward models are central to aligning large language models, yet they often overfit to spurious cues such as response length and overly agreeable tone. Most prior work weakens these cues directly by penalizing or controlling specific…

Self-correction is essential for solving complex reasoning problems in vision-language models (VLMs). However, existing reinforcement learning (RL) methods struggle to learn it, as effective self-correction behaviors emerge only rarely,…

Large language models (LLMs) have attracted significant attention for their exceptional abilities in various natural language processing tasks, but they suffer from hallucinations that will cause performance degradation. One promising…

Large language models have become extremely popular recently due to their ability to achieve strong performance on a variety of tasks, such as text generation and rewriting, but their size and computation cost make them difficult to access,…

Large language model (LLM) agents learn by interacting with environments, but long-horizon training remains fundamentally bottlenecked by sparse and delayed rewards. Existing methods typically address this challenge through post-hoc credit…

Chain-of-thought (CoT) has proven to improve the reasoning capability of large language models (LLMs). However, due to the complexity of multimodal scenarios and the difficulty in collecting high-quality CoT data, CoT reasoning in…

Large language models (LLMs) have achieved notable success in code generation. However, they still frequently produce uncompilable output because their next-token inference procedure does not model formal aspects of code. Although…

Reasoning is a fundamental capability of Large Language Models. While prior research predominantly focuses on enhancing narrow skills like math or code generation, improving performance on many other reasoning tasks remains challenging due…

Going beyond mimicking limited human experiences, recent studies show initial evidence that, like humans, large language models (LLMs) are capable of improving their abilities purely by self-correction, i.e., correcting previous responses…

Modern large language models (LLMs) have demonstrated impressive capabilities at sophisticated tasks, often through step-by-step reasoning similar to humans. This is made possible by their strong few and zero-shot abilities -- they can…

Existing self-evolution methods overlook the influence of fine-grained reasoning steps, which leads to the reasoner-verifier gap. The computational inefficiency of Monte Carlo (MC) process supervision further exacerbates the difficulty in…

Can language models improve their reasoning performance without external rewards, using only their own sampled responses for training? We show that they can. We propose Self-evolving Post-Training (SePT), a simple post-training method that…

Controllable text generation systems often leverage control codes to direct various properties of the output like style and length. Inspired by recent work on causal inference for NLP, this paper reveals a previously overlooked flaw in…

We present a new method for large language models to solve compositional tasks. Although they have shown strong performance on traditional language understanding tasks, large language models struggle to solve compositional tasks, where the…