Related papers: GAST: Gradient-aligned Sparse Tuning of Large Lang…
We introduce BitFit, a sparse-finetuning method where only the bias-terms of the model (or a subset of them) are being modified. We show that with small-to-medium training data, applying BitFit on pre-trained BERT models is competitive with…
Large language models (LLMs) often exhibit performance disparities across languages, with naive multilingual fine-tuning frequently degrading performance due to negative cross-lingual interference. To address this, we introduce COMPASS…
Text-rich graphs, which exhibit rich textual information on nodes and edges, are prevalent across a wide range of real-world business applications. Large Language Models (LLMs) have demonstrated remarkable abilities in understanding text,…
LLM-powered conversational assistants are often deployed in a one-size-fits-all manner, which fails to accommodate individual user preferences. Recently, LLM personalization -- tailoring models to align with specific user preferences -- has…
One-size-fits-all large language models (LLMs) are increasingly being used to help people with their writing. However, the style these models are trained to write in may not suit all users or use cases. LLMs would be more useful as writing…
Pre-trained vision models (PVMs) have demonstrated remarkable adaptability across a wide range of downstream vision tasks, showcasing exceptional performance. However, as these models scale to billions or even trillions of parameters,…
As large language models (LLMs) continue to grow, the cost of full-parameter fine-tuning has made parameter-efficient fine-tuning (PEFT) the default strategy for downstream adaptation. Constraints from inference latency in scalable serving…
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…
Fine-tuning large language models (LLMs) is essential for enhancing their performance on specific tasks but is often resource-intensive due to redundant or uninformative data. To address this inefficiency, we introduce DELIFT (Data…
The alignment of large language models (LLMs) is crucial not only for unlocking their potential in specific tasks but also for ensuring that responses meet human expectations and adhere to safety and ethical principles. Current alignment…
Alignment, endowing a pre-trained Large language model (LLM) with the ability to follow instructions, is crucial for its real-world applications. Conventional supervised fine-tuning (SFT) methods formalize it as causal language modeling…
Pre-trained models (PTMs) have achieved great success in various Software Engineering (SE) downstream tasks following the ``pre-train then fine-tune'' paradigm. As fully fine-tuning all parameters of PTMs can be computationally expensive, a…
We present Adjacent Possible Exploration (APE), a selective fine-tuning method for adapting large language models that systematically explores parameter modifications while maintaining model stability. Inspired by evolutionary optimization…
Open-vocabulary semantic segmentation seeks to label each pixel in an image with arbitrary text descriptions. Vision-language foundation models, especially CLIP, have recently emerged as powerful tools for acquiring open-vocabulary…
Supervised fine-tuning (SFT) has become a crucial step for aligning pretrained large language models (LLMs) using supervised datasets of input-output pairs. However, despite being supervised, SFT is inherently limited by its generative…
Incremental learning aims to adapt to new sets of categories over time with minimal computational overhead. Prior work often addresses this task by training efficient task-specific adaptors that modify frozen layer weights or features to…
Supervised fine-tuning (SFT) is a critical step in aligning large language models (LLMs) with human instructions and values, yet many aspects of SFT remain poorly understood. We trained a wide range of base models on a variety of datasets…
Large language models exhibit strong reasoning capabilities, yet often rely on shortcuts such as surface pattern matching and answer memorization rather than genuine logical inference. We propose Shortcut-Aware Reasoning Training (SART), a…
Models that generate natural language explanations (NLEs) for their predictions have recently gained increasing interest. However, this approach usually demands large datasets of human-written NLEs for the ground-truth answers at training…
Parameter-efficient fine-tuning (PEFT) has emerged as an effective method for adapting pre-trained language models to various tasks efficiently. Recently, there has been a growing interest in transferring knowledge from one or multiple…