相关论文: One-Pass to Reason: Token Duplication and Block-Sp…

Fine-tuning provides an effective means to specialize pre-trained models for various downstream tasks. However, fine-tuning often incurs high memory overhead, especially for large transformer-based models, such as LLMs. While existing…

As the widespread adoption of Large Language Models (LLMs) accelerates, token consumption from intermediate reasoning traces increasingly contributes to inference latency and operational cost. Recent studies suggest that many real-world…

The pretrained large language models (LLMs) are finetuned with labeled data for better instruction following ability and alignment with human values. In this paper, we study the learning dynamics of LLM finetuning on reasoning tasks and…

Understanding the decision-making processes of large language models (LLMs) is essential for their trustworthy development and deployment. However, current interpretability methods often face challenges such as low resolution and high…

Achieving human-level performance on some of the Machine Reading Comprehension (MRC) datasets is no longer challenging with the help of powerful Pre-trained Language Models (PLMs). However, the internal mechanism of these artifacts remains…

While Chain-of-Thought (CoT) prompting improves reasoning in large language models (LLMs), the excessive length of reasoning tokens increases latency and KV cache memory usage, and may even truncate final answers under context limits. We…

The emergence of discourse-like tokens such as "wait" and "therefore" in large language models (LLMs) has offered a unique window into their reasoning processes. However, systematic analyses of how such signals vary across training…

Recent studies have shown that Large Language Models (LLMs) can achieve strong reasoning performance by incorporating functional symbolic representations that abstractly describe graph traversal algorithms and step-by-step reasoning in…

Model adaptation is crucial to handle the discrepancy between proxy training data and actual users data received. To effectively perform adaptation, textual data of users is typically stored on servers or their local devices, where…

Large language models (LLMs) increasingly rely on thinking models that externalize intermediate steps and allocate extra test-time compute, with think-twice strategies showing that a deliberate second pass can elicit stronger reasoning. In…

Recent advancements in large reasoning models (LRMs) have demonstrated the effectiveness of scaling test-time computation to enhance reasoning capabilities on various tasks. However, LRMs often suffer from an ``overthinking'' problem, where…

Recent advancements in cognitive science and multi-round reasoning techniques for Large Language Models (LLMs) suggest that iterative thinking processes improve problem-solving performance in complex tasks. Inspired by this, approaches like…

Large language models (LLMs) have been routinely used to solve various tasks using step-by-step reasoning. However, the structure of intermediate reasoning steps, or thoughts, is rigid and unidirectional, such as chains, trees, or…

The scalability of large language models for long-context reasoning is severely constrained by the linear growth of their Transformer key-value cache, which incurs significant memory and computational costs. We posit that as a model…

Despite the advancements in in-context learning (ICL) for large language models (LLMs), current research centers on specific prompt engineering, such as demonstration selection, with the expectation that a single iteration of demonstrations…

Reasoning is essential for effective communication and decision-making. While recent advances in LLMs and MLLMs have shown that incorporating explicit reasoning significantly improves understanding and generalization, reasoning in LSMs…

Unified architectures in multimodal large language models (MLLM) have shown promise in handling diverse tasks within a single framework. In the text-to-speech (TTS) task, current MLLM-based approaches rely on discrete token representations,…

Recent Large Reasoning Models (LRMs), such as DeepSeek-R1 and OpenAI o1, have demonstrated strong performance gains by scaling up the length of Chain-of-Thought (CoT) reasoning during inference. However, a growing concern lies in their…

Large language models (LLMs) tackle complex tasks by generating long chains of thought or "reasoning traces" that act as latent variables in the generation of an output given a query. A model's ability to generate such traces can be…

Large language models (LLMs) excel on a variety of reasoning benchmarks, but previous studies suggest they sometimes struggle to generalize to unseen questions, potentially due to over-reliance on memorized training examples. However, the…