Related papers: Prototype-Based Dynamic Steering for Large Languag…
Chain-of-thought (CoT) prompting has been extended to large audio-language models (LALMs) to elicit reasoning, yet enhancing its effectiveness without training remains challenging. We study inference-time model steering as a training-free…
Chain-of-Thought (CoT) prompting has improved the reasoning performance of large language models (LLMs), but it remains unclear why it works and whether it is the unique mechanism for triggering reasoning in large language models. In this…
Recent work on activation and latent steering has demonstrated that modifying internal representations can effectively guide large language models (LLMs) toward improved reasoning and efficiency without additional training. However, most…
Large language models can be steered at inference time through prompting or activation interventions, but activation steering methods often underperform compared to prompt-based approaches. We propose a framework that formulates prompt…
Large language models (LLMs) demonstrate strong chain-of-thought (CoT) reasoning abilities, while smaller models (<= 3B parameters) significantly underperform on multi-step reasoning tasks. Based on empirical analyses of the Qwen-2.5 model…
Reinforcement learning (RL) finetuning has become a key technique for enhancing the reasoning abilities of large language models (LLMs). However, its effectiveness critically depends on the selection of training data. Recent advances…
Large language models (LLMs) can perform complex reasoning by generating intermediate reasoning steps. Providing these steps for prompting demonstrations is called chain-of-thought (CoT) prompting. CoT prompting has two major paradigms. One…
Large Language Models (LLMs) often rely on long chain-of-thought (CoT) reasoning to solve complex tasks. While effective, these trajectories are frequently inefficient, leading to high latency from excessive token generation, or unstable…
This paper investigates how Large Language Models (LLMs) represent non-English tokens -- a question that remains underexplored despite recent progress. We propose a lightweight intervention method using representation steering, where a…
Large Language Models (LLMs) are important tools for reasoning and problem-solving, while they often operate passively, answering questions without actively discovering new ones. This limitation reduces their ability to simulate human-like…
Current large-language models (LLMs) typically adopt a fixed reasoning strategy, either simple or complex, for all questions, regardless of their difficulty. This neglect of variation in task and reasoning process complexity leads to an…
Activation steering methods enable inference-time control of large language model (LLM) behavior without retraining, but current approaches face a fundamental trade-off: sample-efficient methods suboptimally capture steering signals from…
Large Language Models (LLMs) have demonstrated remarkable performance across diverse tasks and exhibited impressive reasoning abilities by applying zero-shot Chain-of-Thought (CoT) prompting. However, due to the evolving nature of sentence…
Role-playing has emerged as an effective technique for enhancing the reasoning capabilities of large language models (LLMs). However, existing methods primarily rely on prompt engineering, which often lacks stability and interpretability.…
Reflection, the ability of large language models (LLMs) to evaluate and revise their own reasoning, has been widely used to improve performance on complex reasoning tasks. Yet, most prior works emphasizes designing reflective prompting…
Activation steering methods control large language model (LLM) behavior by modifying internal activations at inference time. However, most existing activation steering methods rely on a fixed steering strength, leading to either…
Large Language Models employing extended chain-of-thought (CoT) reasoning often suffer from the overthinking phenomenon, generating excessive and redundant reasoning steps that increase computational costs while potentially degrading…
We propose cognitive prompting as a novel approach to guide problem-solving in large language models (LLMs) through structured, human-like cognitive operations, such as goal clarification, decomposition, filtering, abstraction, and pattern…
Preference alignment is a critical step in making Large Language Models (LLMs) useful and aligned with (human) preferences. Existing approaches such as Reinforcement Learning from Human Feedback or Direct Preference Optimization typically…
Large language models (LLMs) have shown impressive abilities in leveraging pretrained knowledge through prompting, but they often struggle with unseen tasks, particularly in data-scarce scenarios. While cross-task in-context learning offers…