Related papers: ATTNChecker: Highly-Optimized Fault Tolerant Atten…

Reinforcement fine-tuning (RFT) has become a core paradigm for post-training large language models, yet its training process remains highly fragile. Existing efforts mainly improve reliability at the system level or address specific issues…

While Large Language Models (LLMs) achieve strong performance across diverse tasks, their inference dynamics remain poorly understood because of the limited resolution of existing analysis tools. In this work, we identify an intrinsic…

Large Language Models (LLMs), such as GPT and LLaMA, introduce unique memory access characteristics during inference due to frequent token sequence lookups and embedding vector retrievals. These workloads generate highly irregular and…

Transformer-based large language models (LLMs) excel in modeling complex language patterns but face significant computational costs during inference, especially with long inputs due to the attention mechanism's memory overhead. We observe…

Air Traffic Control (ATC) is a safety-critical domain in which incorrect interpretation of instructions may lead to severe operational consequences. While large language models (LLMs) demonstrate strong general performance, their…

Fine-tuning large language models (LLMs) improves performance but introduces critical safety vulnerabilities: even minimal harmful data can severely compromise safety measures. We observe that perturbations orthogonal to the alignment…

Transformer-based large language models (LLMs) have achieved strong performance across many natural language processing tasks. Nonetheless, their quadratic computational and memory requirements, particularly in self-attention layers, pose…

Large language models (LLMs) are effective for automated program repair, but plausible patches that pass the full test suite often rewrite more code than necessary, increasing review and maintenance costs. This over-editing is common…

Large Language Models (LLMs), with their increasing depth and number of parameters, have demonstrated outstanding performance across a variety of natural language processing tasks. However, this growth in scale leads to increased…

Fine-tuning Large Language Models (LLMs) adapts a trained model to specific downstream tasks, significantly improving task-specific performance. Supervised Fine-Tuning (SFT) is a common approach, where an LLM is trained to produce desired…

With the rapid advancement of Large Language Models (LLMs), the Chain-of-Thought (CoT) component has become significant for complex reasoning tasks. However, in conventional Supervised Fine-Tuning (SFT), the model could allocate…

Evaluations of large language model (LLM) risks and capabilities are increasingly being incorporated into AI risk management and governance frameworks. Currently, most risk evaluations are conducted by designing inputs that elicit harmful…

We study and quantify the problem of forgetting when fine-tuning pre-trained large language models (LLMs) on a downstream task. We find that parameter-efficient fine-tuning (PEFT) strategies, such as Low-Rank Adapters (LoRA), still suffer…

Machine Learning (ML) is making a strong resurgence in tune with the massive generation of unstructured data which in turn requires massive computational resources. Due to the inherently compute- and power-intensive structure of Neural…

Large Language Models (LLMs) demonstrate exceptional capabilities in a multitude of NLP tasks. However, the efficacy of such models to languages other than English is often limited. Prior works have shown that encoder-only models such as…

While large language models (LLMs) are extensively used, there are raising concerns regarding privacy, security, and copyright due to their opaque training data, which brings the problem of detecting pre-training data on the table. Current…

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…

Large language models (LLMs) are increasingly deployed in safety and security critical applications, raising concerns about their robustness to model parameter fault injection attacks. Recent studies have shown that bit-flip attacks (BFAs),…

Performance evaluation plays a crucial role in the development life cycle of large language models (LLMs). It estimates the model's capability, elucidates behavior characteristics, and facilitates the identification of potential issues and…

Since the advent of ChatGPT, Large Language Models (LLMs) have excelled in various tasks but remain as black-box systems. Understanding the reasoning bottlenecks of LLMs has become a critical challenge, as these limitations are deeply tied…