Related papers: Prototype-Based Dynamic Steering for Large Languag…

Reasoning-enhanced large language models (LLMs) explicitly generate intermediate reasoning steps prior to generating final answers, helping the model excel in complex problem-solving. In this paper, we demonstrate that this emerging…

Prompt-tuning (PT) for large language models (LLMs) can facilitate the performance on various conventional NLP tasks with significantly fewer trainable parameters. However, our investigation reveals that PT provides limited improvement and…

Mathematical reasoning has been challenging for large language models (LLMs), and the introduction of step-by-step Chain-of-Thought (CoT) inference has significantly advanced the mathematical capabilities of LLMs. However, current…

Process Reward Models (PRMs) provide step-level supervision that improves the reliability of reasoning in large language models. While PRMs have been extensively studied in text-based domains, their extension to Vision Language Models…

Large pretrained models are showing increasingly better performance in reasoning and planning tasks across different modalities, opening the possibility to leverage them for complex sequential decision making problems. In this paper, we…

Diffusion large language models (dLLMs) have shown great potential in large-scale language modeling, and there is an increasing interest in further improving the capacity to solve complex problems by guiding the reasoning process step by…

Test-time scaling (TTS) has become an effective approach for improving large language model performance by allocating additional computation during inference. However, existing TTS strategies are largely hand-crafted: researchers manually…

Prompting methods play a crucial role in enhancing the capabilities of pre-trained large language models (LLMs). We explore how contrastive prompting (CP) significantly improves the ability of large language models to perform complex…

Steering has emerged as a practical approach to enable post-hoc guidance of LLMs towards enforcing a specific behavior. However, it remains largely underexplored for multimodal LLMs (MLLMs); furthermore, existing steering techniques, such…

Chain of Thought (CoT) prompting has been shown to significantly improve the performance of large language models (LLMs), particularly in arithmetic and reasoning tasks, by instructing the model to produce intermediate reasoning steps.…

Steering language models (LMs) by modifying internal activations is a popular approach for controlling text generation. Unsupervised dictionary learning methods, e.g., sparse autoencoders, can be scaled to produce many steering vectors, but…

Reinforcement Learning (RL) has made significant strides in enabling artificial agents to learn diverse behaviors. However, learning an effective policy often requires a large number of environment interactions. To mitigate sample…

Pre-trained language models (LMs) are able to perform complex reasoning without explicit fine-tuning. To understand how pre-training with a next-token prediction objective contributes to the emergence of such reasoning capability, we…

Recent advancements in large language models (LLMs) have resulted in increasingly anthropomorphic language concerning the ability of LLMs to reason. Whether reasoning in LLMs should be understood to be inherently different is, however,…

Chain-of-thought (CoT) reasoning enables large language models (LLMs) to break down complex problems into interpretable intermediate steps, significantly enhancing model transparency and performance in reasoning tasks. However, conventional…

Recently, the development of large language models (LLMs) has been significantly enhanced the question answering and dialogue generation, and makes them become increasingly popular in current practical scenarios. While unlike the general…

Length control in Large Language Models (LLMs) is a crucial but under-addressed challenge, with applications ranging from voice interfaces requiring concise responses to research summaries needing comprehensive outputs. Current approaches…

Researchers have been studying approaches to steer the behavior of Large Language Models (LLMs) and build personalized LLMs tailored for various applications. While fine-tuning seems to be a direct solution, it requires substantial…

Scaling model size and training data has led to great advances in the performance of Large Language Models (LLMs). However, the diminishing returns of this approach necessitate alternative methods to improve model capabilities, particularly…

Large Language Models (LLMs) and Multimodal LLMs (MLLMs) have demonstrated immense potential in autonomous driving (AD) by offering human-like reasoning and open-world generalization. However, the excessive computational overhead and high…