Related papers: Internal states before wait modulate reasoning pat…

Understanding how Large Language Models (LLMs) perform logical reasoning internally remains a fundamental challenge. While prior mechanistic studies focus on identifying taskspecific circuits, they leave open the question of what…

Do reasoning models have "Aha!" moments? Prior work suggests that models like DeepSeek-R1-Zero undergo sudden mid-trace realizations that lead to accurate outputs, implying an intrinsic capacity for self-correction. Yet, it remains unclear…

Current large language models can perform reasonably well on complex tasks that require step-by-step reasoning with few-shot learning. Are these models applying reasoning skills they have learnt during pre-training and reason outside of…

While there is much recent interest in studying why Transformer-based large language models make predictions the way they do, the complex computations performed within each layer have made their behavior somewhat opaque. To mitigate this…

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…

Chain-of-Thought (CoT) is a critical technique in enhancing the reasoning ability of Large Language Models (LLMs), and latent reasoning methods have been proposed to accelerate the inefficient token-level reasoning chain. We notice that…

Recent advances in large reasoning models have enabled complex, step-by-step reasoning but often introduce significant overthinking, resulting in verbose and redundant outputs that hinder efficiency. In this study, we examine whether…

Reward modeling is essential for aligning large language models with human preferences through reinforcement learning. To provide accurate reward signals, a reward model (RM) should stimulate deep thinking and conduct interpretable…

Recent language models exhibit strong reasoning capabilities, yet the influence of long-context capacity on reasoning remains underexplored. In this work, we hypothesize that current limitations in reasoning stem, in part, from insufficient…

Recent reasoning language models, particularly those that employ long latent chains of thought, achieve strong performance on complex agentic tasks. However, as these models operate over increasingly long time horizons, their internal…

OpenAI o1 has shown that applying reinforcement learning to integrate reasoning steps directly during inference can significantly improve a model's reasoning capabilities. This result is exciting as the field transitions from the…

In recent years, large pretrained models have been used in dialogue systems to improve successful task completion rates. However, lack of reasoning capabilities of dialogue platforms make it difficult to provide relevant and fluent…

The underperformance of existing multimodal large language models for time series reasoning lies in the absence of rationale priors that connect temporal observations to their downstream outcomes, which leads models to rely on superficial…

Chain-of-thought (CoT) reasoning has enabled large language models (LLMs) to utilize additional computation through intermediate tokens to solve complex tasks. However, we posit that typical reasoning traces contain many redundant tokens,…

Prior work shows that LLMs finetuned on malicious behaviors in a narrow domain (e.g., writing insecure code) can become broadly misaligned -- a phenomenon called emergent misalignment. We investigate whether this extends from conventional…

With the advancement of large language models (LLMs), their performance on multiple-choice question (MCQ) tasks has improved significantly. However, existing approaches face key limitations: answer choices are typically presented to LLMs…

The recent advancements in Deep Learning models and techniques have led to significant strides in performance across diverse tasks and modalities. However, while the overall capabilities of models show promising growth, our understanding of…

Transformers have demonstrated remarkable performance in natural language processing and related domains, as they largely focus on sequential, autoregressive next-token prediction tasks. Yet, they struggle in logical reasoning, not…

Recently, techniques such as explicit structured reasoning have demonstrated strong test-time scaling behavior by enforcing a separation between the model's internal "thinking" process and the final response. A key factor influencing answer…

Recent advances in Large Audio-Language Models (LALMs) have made real-time, streaming spoken interaction increasingly practical. In this setting, reasoning quality and responsiveness are tightly coupled: delaying reasoning until the speech…