相关论文: Auto-Patching: Enhancing Multi-Hop Reasoning in La…

Data mixing augmentation have proved to be effective in improving the generalization ability of deep neural networks. While early methods mix samples by hand-crafted policies (e.g., linear interpolation), recent methods utilize saliency…

We investigate the ability of language models to perform compositional reasoning tasks where the overall solution depends on correctly composing the answers to sub-problems. We measure how often models can correctly answer all sub-problems…

Improving Multi-modal Large Language Models (MLLMs) in the post-training stage typically relies on supervised fine-tuning (SFT) or reinforcement learning (RL), which require expensive and manually annotated multi-modal data--an ultimately…

Large Language Models (LLMs) have reshaped natural language processing, powering applications from multi-hop retrieval and question answering to autonomous agent workflows. Yet, prompt engineering -- the task of crafting textual inputs to…

Large Language Models (LLMs) have demonstrated strong capabilities for hidden representation interpretation through Patchscopes, a framework that uses LLMs themselves to generate human-readable explanations by decoding from internal hidden…

Current state-of-the-art solvers for mixed-integer programming (MIP) problems are designed to perform well on a wide range of problems. However, for many real-world use cases, problem instances come from a narrow distribution. This has…

Hybrid planner switching framework (HPSF) for autonomous driving needs to reconcile high-speed driving efficiency with safe maneuvering in dense traffic. Existing HPSF methods often fail to make reliable mode transitions or sustain…

In recent years, patch representation learning has emerged as a necessary research direction for exploiting the capabilities of machine learning in software generation. These representations have driven significant performance enhancements…

Large Language Models (LLMs) have shown impressive abilities in various tasks. However, fundamentally improving them depends on high-quality datasets or computationally expensive fine-tuning. On the contrary, humans can easily improve…

While large language models (LLMs) demonstrate remarkable success in multilingual translation, their internal core translation mechanisms, even at the fundamental word level, remain insufficiently understood. To address this critical gap,…

Large Language Models (LLMs) with chain-of-thought (COT) prompting have demonstrated impressive abilities on simple nature language inference tasks. However, they tend to perform poorly on Multi-hop Question Answering (MHQA) tasks due to…

The pre-trained multi-lingual XLSR model generalizes well for language identification after fine-tuning on unseen languages. However, the performance significantly degrades when the languages are not very distinct from each other, for…

Large Language Models (LLMs) have exhibited an impressive capability to perform reasoning tasks, especially if they are encouraged to generate a sequence of intermediate steps. Reasoning performance can be improved by suitably combining…

The newly released OpenAI-o1 and DeepSeek-R1 have demonstrated that test-time scaling can significantly improve model performance, especially in complex tasks such as logical reasoning. Common test-time scaling methods involve generating…

Recent advances in large language models (LLMs) have introduced latent reasoning as a promising alternative to autoregressive reasoning. By performing internal computation with hidden states from previous steps, latent reasoning benefit…

Retrieval-augmented generation (RAG) systems have made significant progress in solving complex multi-hop question answering (QA) tasks in the English scenario. However, RAG systems inevitably face the application scenario of retrieving…

We present a controlled study of multi-hop contextual reasoning in large language models, providing a clean demonstration of the task-method dissociation: rule-based pattern matching achieves 100% success on structured information retrieval…

Automated Program Repair (APR) seeks to automatically correct software bugs without requiring human intervention. However, existing tools tend to generate patches that satisfy test cases without fixing the underlying bug, those are known as…

Explicit Chain-of-Thought improves the reasoning performance of large language models but often incurs high inference cost due to verbose token-level traces. While recent approaches reduce this overhead via concise prompting or step…

In this work, we propose a novel method named \textbf{Auto}mated \textbf{P}rocess-\textbf{S}upervised \textbf{V}erifier (\textbf{\textsc{AutoPSV}}) to enhance the reasoning capabilities of large language models (LLMs) by automatically…