11 accepted papers
In the big-world regime, agents cannot be universally capable and their ability is inevitably specialized across a world in pieces. Consequently, standard uniform guarantees fail to distinguish between the understanding of critical bottlenecks and irrelevant failures. We first formalize this limitat…
Low-Rank Adaptation (LoRA) is a widely used parameter-efficient fine-tuning technique, and previous works have studied the update dynamics of LoRA, showing that updating via the low-rank matrix $\mathbf{A}$ can be viewed as a process within the compressed subspace defined by $\mathbf{A}^{\top} \math…
In recent years, the proliferation of renewable energy sources has heightened the focus on networked energy systems. These systems face significant challenges due to the unpredictable nature of energy generation and consumption, as well as the complexity of managing numerous components and parameter…
Hallucination occurs when large language models exhibit behavior that deviates from the boundaries of their knowledge during response generation. To address this critical issue, previous learning-based methods attempt to finetune models but are limited by off-policy sampling and coarse-grained feedb…
Reward Models (RMs) are crucial for aligning language models with human preferences. Currently, the evaluation of RMs depends on measuring accuracy against a validation set of manually annotated preference data. Although this method is straightforward and widely adopted, the relationship between RM…
The use of denoising diffusion models is becoming increasingly popular in the field of image editing. However, current approaches often rely on either image-guided methods, which provide a visual reference but lack control over semantic consistency, or text-guided methods, which ensure alignment wit…
As post-training processes utilize increasingly large datasets and base models continue to grow in size, the computational demands and implementation challenges of existing algorithms are escalating significantly. In this paper, we propose modeling the changes at the logits level during post-trainin…
In-context learning(ICL) has gained considerable attention due to its data efficiency and task adaptability. Unfortunately, ICL suffers from the demonstration bias, i.e., its performance and robustness are severely affected by the selection and ordering of demonstrations. In this paper, we identify…
Knowledge Graphs (KGs) often suffer from incomplete knowledge, which which restricts their utility. Recently, Contrastive Learning (CL) has been introduced to Knowledge Graph Completion (KGC), significantly improving the discriminative capabilities of KGC models and setting new benchmarks in perform…
The alignment problem in Large Language Models (LLMs) involves adapting them to the broad spectrum of human values. This requirement challenges existing alignment methods due to diversity of preferences and regulatory standards. This paper introduces a novel alignment paradigm, priority rule followi…
The availability of parallel sentence simplification (SS) is scarce for neural SS modelings. We propose an unsupervised method to build SS corpora from large-scale bilingual translation corpora, alleviating the need for SS supervised corpora. Our method is motivated by the following two findings: ne…