Related papers: BBox-Adapter: Lightweight Adapting for Black-Box L…

Deploying language models (LMs) in customer-facing speech applications requires conversational fluency and adherence to specific stylistic guidelines. This can be challenging to achieve reliably using complex system prompts due to issues…

The increasing scale of general-purpose Pre-trained Language Models (PLMs) necessitates the study of more efficient adaptation across different downstream tasks. In this paper, we establish a Black-box Discrete Prompt Learning (BDPL) to…

We introduce the Concept Bottleneck Large Language Model (CB-LLM), a pioneering approach to creating inherently interpretable Large Language Models (LLMs). Unlike traditional black-box LLMs that rely on post-hoc interpretation methods with…

Building generalizable AI models is one of the primary challenges in the healthcare domain. While radiologists rely on generalizable descriptive rules of abnormality, Neural Network (NN) models suffer even with a slight shift in input…

Large language models (LLMs) have garnered significant interest in natural language processing (NLP), particularly their remarkable performance in various downstream tasks in resource-rich languages. Recent studies have highlighted the…

Cross-lingual speech adaptation aims to solve the problem of leveraging multiple rich-resource languages to build models for a low-resource target language. Since the low-resource language has limited training data, speech recognition…

Fine-tuning Pre-trained protein language models (PLMs) has emerged as a prominent strategy for enhancing downstream prediction tasks, often outperforming traditional supervised learning approaches. As a widely applied powerful technique in…

The current study describes a cost-effective method for adapting large language models (LLMs) for academic advising with study-abroad contexts in mind and for application in low-resource methods for acculturation. With the…

The capabilities of Large Language Models (LLMs) in low-resource languages lag far behind those in English, making their universal accessibility a significant challenge. To alleviate this, we present $\textit{Franken-Adapter}$, a modular…

Gradient-based optimization is the workhorse of deep learning, offering efficient and scalable training via backpropagation. However, exposing gradients during training can leak sensitive information about the underlying data, raising…

Large language models (LLMs) are increasingly explored for NP-hard combinatorial optimization problems, but most existing methods emphasize feasible-instance solution generation and do not explicitly address infeasibility detection. We…

Training or finetuning large-scale language models (LLMs) requires substantial computation resources, motivating recent efforts to explore parameter-efficient adaptation to downstream tasks. One approach is to treat these models as black…

A wide variety of natural language tasks are currently being addressed with large-scale language models (LLMs). These models are usually trained with a very large amount of unsupervised text data and adapted to perform a downstream natural…

Extremely large pre-trained language models (PTMs) such as GPT-3 are usually released as a service. It allows users to design task-specific prompts to query the PTMs through some black-box APIs. In such a scenario, which we call…

Large Language Model (LLM) alignment conventionally relies on supervised fine-tuning or reinforcement learning based alignment frameworks. These methods typically require labeled or preference datasets and involve updating model weights to…

A brain-computer interface (BCI) system usually needs a long calibration session for each new subject/task to adjust its parameters, which impedes its transition from the laboratory to real-world applications. Domain adaptation, which…

In this work, we show a fundamental limitation in vocabulary adaptation approaches that use Byte-Pair Encoding (BPE) tokenization scheme for fine-tuning pretrained language models (PLMs) to expert domains. Current approaches trivially…

This paper introduces a method for adapting LoRA adapters in smaller-sized language models to arbitrary downstream tasks. Unlike standard mixture-of-expert architectures, our method employs a gradient-free routing function to choose a…

Source-Free domain adaptation transits the source-trained model towards target domain without exposing the source data, trying to dispel these concerns about data privacy and security. However, this paradigm is still at risk of data leakage…

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…