相关论文: Diagnosing Training Inference Mismatch in LLM Rein…

Large language models (LLMs) exhibit remarkable capabilities across diverse tasks, yet aligning them efficiently and effectively with human expectations remains a critical challenge. This thesis advances LLM alignment by introducing novel…

Large Language Models (LLMs) display strikingly different generalization behaviors: supervised fine-tuning (SFT) often narrows capability, whereas reinforcement-learning (RL) tuning tends to preserve it. The reasons behind this divergence…

Accurate clinical coding is essential for healthcare documentation, billing, and decision-making. While prior work shows that off-the-shelf LLMs struggle with this task, evaluations based on exact match metrics often overlook errors where…

Modern large language models (LLMs) are often evaluated and deployed under a one-shot, greedy inference protocol, especially in professional settings that require deterministic behavior. This regime can systematically under-estimate a fixed…

Preference alignment methods are increasingly critical for steering large language models (LLMs) to generate outputs consistent with human values. While recent approaches often rely on synthetic data generated by LLMs for scalability and…

Existing training-time safety alignment techniques for large language models (LLMs) remain vulnerable to jailbreak attacks. Direct preference optimization (DPO), a widely deployed alignment method, exhibits limitations in both experimental…

Despite the strong reasoning ability of large language models~(LLMs), they are prone to errors and hallucinations. As a result, how to check their outputs effectively and efficiently has become a critical problem in their applications.…

Large Language Models (LLMs) are increasingly deployed to automatically label and analyze educational dialogue at scale, yet current pipelines lack reliable ways to detect when models are wrong. We investigate whether reasoning generated by…

Data mixing strategies (e.g., CutMix) have shown the ability to greatly improve the performance of convolutional neural networks (CNNs). They mix two images as inputs for training and assign them with a mixed label with the same ratio.…

Tangled code changes, commits that conflate unrelated modifications such as bug fixes, refactorings, and enhancements, introduce significant noise into bug datasets and adversely affect the performance of bug prediction models. Addressing…

The availability of large pre-trained models is changing the landscape of Machine Learning research and practice, moving from a training-from-scratch to a fine-tuning paradigm. While in some applications the goal is to "nudge" the…

The memorization of training data in large language models (LLMs) poses significant privacy and copyright concerns. Existing data extraction methods, particularly heuristic-based divergence attacks, often exhibit limited success and offer…

When adapting ICL with or without fine-tuning, we are curious about whether the instruction-tuned language model is able to achieve well-calibrated results without suffering from the problem of overconfidence (i.e., miscalibration)…

Large language models (LLMs) have shown strong performance in Verilog generation from natural language description. However, ensuring the functional correctness of the generated code remains a significant challenge. This paper introduces a…

Fine-tuning a general-purpose large language model (LLM) for a specific domain or task has become a routine procedure for ordinary users. However, fine-tuning is known to remove the safety alignment features of the model, even when the…

Research in machine learning is making progress in fixing its own reproducibility crisis. Reinforcement learning (RL), in particular, faces its own set of unique challenges. Comparison of point estimates, and plots that show successful…

Tool-augmented Language Models (TaLMs) can invoke external tools to solve problems beyond their parametric capacity. However, it remains unclear whether these tool-enabled gains reflect trustworthy reasoning. Focusing on the Code…

Model-based reinforcement learning (MBRL) has been shown to be a powerful framework for data-efficiently learning control of continuous tasks. Recent work in MBRL has mostly focused on using more advanced function approximators and planning…

Finetuning large language models on narrowly harmful datasets can cause them to become emergently misaligned, giving stereotypically `evil' responses across diverse unrelated settings. Concerningly, a pre-registered survey of experts failed…

Outcome-reward reinforcement learning (RL) has proven effective at improving the reasoning capabilities of large language models (LLMs). However, standard RL assigns credit only at the level of the final answer, penalizing entire reasoning…