Related papers: FineSteer: A Unified Framework for Fine-Grained In…
Large Reasoning Models (LRMs) exhibit human-like cognitive reasoning strategies (e.g. backtracking, cross-verification) during reasoning process, which improves their performance on complex tasks. Currently, reasoning strategies are…
When using supervised fine-tuning (SFT) to adapt large language models (LLMs) to specific domains, a significant challenge arises: should we use the entire SFT dataset for fine-tuning? Common practice often involves fine-tuning directly on…
Safety fine-tuning helps align Large Language Models (LLMs) with human preferences for their safe deployment. To better understand the underlying factors that make models safe via safety fine-tuning, we design a synthetic data generation…
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…
Recent advances in Large Reasoning Models (LRMs) have demonstrated remarkable capabilities in solving complex tasks such as mathematics and coding. However, these models frequently exhibit a phenomenon known as overthinking during…
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) encode vast amounts of parametric knowledge during pre-training. As world knowledge evolves, effective deployment increasingly depends on their ability to faithfully follow externally retrieved context. When…
Realizing personalized intelligence faces a core dilemma: sending user history to centralized large language models raises privacy concerns, while on-device small language models lack the reasoning capacity required for high-quality…
Synthesizing high-quality instruction data from unsupervised text is a promising paradigm for training large language models (LLMs), yet automated methods for this task still exhibit significant limitations in the diversity and difficulty…
Large language models (LLMs) are a promising avenue for machine translation (MT). However, current LLM-based MT systems are brittle: their effectiveness highly depends on the choice of few-shot examples and they often require extra…
Ensemble learning of LLMs has emerged as a promising alternative to enhance performance, but existing approaches typically treat models as black boxes, combining the inputs or final outputs while overlooking the rich internal…
Deep learning has contributed remarkably to the advancement of time series analysis. Still, deep models can encounter performance bottlenecks in real-world data-scarce scenarios, which can be concealed due to the performance saturation with…
In the evolving landscape of transportation systems, integrating Large Language Models (LLMs) offers a promising frontier for advancing intelligent decision-making across various applications. This paper introduces a novel 3-dimensional…
Large language models deliver strong generative performance but at the cost of massive parameter counts, memory use, and decoding latency. Prior work has shown that pruning and structured sparsity can preserve accuracy under substantial…
The prevailing approach to aligning Large Language Models (LLMs) typically relies on human or AI feedback and assumes access to specific types of preference datasets. In our work, we question the efficacy of such datasets and explore…
Large Language Models (LLMs) demonstrate strong performance in real-world applications, yet existing open-source instruction datasets often concentrate on narrow domains, such as mathematics or coding, limiting generalization and widening…
Recent large language models (LLM) are leveraging human feedback to improve their generation quality. However, human feedback is costly to obtain, especially during inference. In this work, we propose LLMRefine, an inference time…
This work introduces SteerVLM, a lightweight steering module designed to guide Vision-Language Models (VLMs) towards outputs that better adhere to desired instructions. Our approach learns from the latent embeddings of paired prompts…
Large language models (LLMs) exhibit remarkable capabilities in handling natural language tasks; however, they may struggle to consistently follow complex instructions including those involve multiple constraints. Post-training LLMs using…
Activation engineering enables precise control over Large Language Models (LLMs) without the computational cost of fine-tuning. However, existing methods deriving vectors from static activation differences are susceptible to…