Related papers: Beyond Rejection Sampling: Trajectory Fusion for S…

Supervised fine-tuning (SFT) is crucial for adapting Large Language Models (LLMs) to specific tasks. In this work, we demonstrate that the order of training data can lead to significant training imbalances, potentially resulting in…

With the proliferation of location-tracking technologies, massive volumes of trajectory data are continuously being collected. As a fundamental task in trajectory data mining, trajectory similarity computation plays a critical role in a…

Large language models (LLMs) combined with instruction tuning have shown significant progress in information extraction (IE) tasks, exhibiting strong generalization capabilities to unseen datasets by following annotation guidelines.…

Reinforcement finetuning (RFT) has become a standard approach for enhancing the reasoning capabilities of large language models (LLMs). However, its impact on model trustworthiness remains underexplored. In this work, we identify and…

The inherent capabilities of a language model (LM) and the reasoning strategies it employs jointly determine its performance in reasoning tasks. While test-time scaling is regarded as an effective approach to tackling complex reasoning…

Instruction tuning is critical to large language models (LLMs) for achieving better instruction following and task adaptation capabilities but its success heavily relies on the training data quality. Many recent methods focus on improving…

Large Language Models (LLMs) are changing the coding paradigm, known as vibe coding, yet synthesizing algorithmically sophisticated and robust code still remains a critical challenge. Incentivizing the deep reasoning capabilities of LLMs is…

Large language models are increasingly used for complex reasoning tasks where high-quality offline data such as expert-annotated solutions and distilled reasoning traces are often available. However, in environments with sparse rewards,…

Large Language Models (LLMs) are typically fine-tuned for reasoning tasks through a two-stage pipeline of Supervised Fine-Tuning (SFT) followed by Reinforcement Learning (RL), a process fraught with catastrophic forgetting and suboptimal…

Large language models (LLMs) primarily rely on supervised fine-tuning (SFT) as a key method to adapt pre-trained models to domain-specific tasks such as mathematical reasoning. However, standard SFT uniformly penalizes all tokens,…

Large language models (LLMs) exhibit complementary strengths arising from differences in pretraining data, model architectures, and decoding behaviors. Inference-time ensembling provides a practical way to combine these capabilities without…

Sequential fine-tuning and multi-task learning are methods aiming to incorporate knowledge from multiple tasks; however, they suffer from catastrophic forgetting and difficulties in dataset balancing. To address these shortcomings, we…

Reinforcement Learning (RL) and Supervised Fine-Tuning (SFT) are the two dominant paradigms for enhancing Large Language Model (LLM) performance on downstream tasks. While RL generally preserves broader model capabilities (retention) better…

Large language models (LLMs) have been increasingly used to analyze text. However, they are often plagued with contextual reasoning limitations when analyzing long documents. When long documents are processed sequentially, early or dominant…

Scaling test-time compute via long Chain-of-Thought unlocks remarkable gains in reasoning capabilities, yet it faces practical limits due to the linear growth of KV cache and quadratic attention complexity. In this paper, we introduce…

The growing disparity between the exponential scaling of computational resources and the finite growth of high-quality text data now constrains conventional scaling approaches for large language models (LLMs). To address this challenge, we…

Retrieval-augmented generation (RAG) enhances large language models (LLMs) by integrating external knowledge retrieved from a knowledge base. However, its effectiveness is fundamentally constrained by the reliability of both the retriever…

Diffusion large language models (dLLMs) have emerged as a new architecture following auto regressive models. Their denoising process offers a powerful generative advantage, but they present significant challenges in learning and…

This work characterizes large language models' chain-of-thought generation as a structured trajectory through representation space. We show that mathematical reasoning traverses functionally ordered, step-specific subspaces that become…

Inference-time scaling techniques have significantly bolstered the reasoning capabilities of large language models (LLMs) by harnessing additional computational effort at inference without retraining. Similarly, Chain-of-Thought (CoT)…