Related papers: Data Difficulty and the Generalization--Extrapolat…
Recent alignment work on Large Language Models (LLMs) suggests preference optimization can improve reasoning by shifting probability mass toward better solutions. We test this claim in a resource-constrained setting by applying GRPO with…
This paper explores a scientific question in supervised fine-tuning (SFT): why SFT is broadly effective for small-scale deep neural networks, yet can produce inconsistent or even detrimental effects when applied to large language models…
This paper surveys research works in the quickly advancing field of instruction tuning (IT), which can also be referred to as supervised fine-tuning (SFT)\footnote{In this paper, unless specified otherwise, supervised fine-tuning (SFT) and…
Large language models (LLMs) acquire substantial world knowledge during pre-training, which is further shaped by post-training techniques such as supervised fine-tuning (SFT). However, the impact of SFT on a model's knowledge remains…
Fine-tuning large language models (LLMs) using diverse datasets is crucial for enhancing their overall performance across various domains. In practical scenarios, existing methods based on modeling the mixture proportions of data…
The increasing demand for domain-specific and human-aligned Large Language Models (LLMs) has led to the widespread adoption of Supervised Fine-Tuning (SFT) techniques. SFT datasets often comprise valuable instruction-response pairs, making…
This paper introduces a multifaceted methodology for fine-tuning and evaluating large language models (LLMs) for specialized monetization tasks. The goal is to balance general language proficiency with domain-specific skills. The…
Supervised Fine-Tuning (SFT) is widely used for task-specific adaptation, yet recent work shows it systematically undermines reasoning generalization. We argue the root cause is not memorization itself, but its target: vanilla SFT drives…
Scaling the amount of data used for supervied fine-tuning(SFT) does not guarantee the proportional gains in model performance, highlighting a critical need to understand what makes training samples effective. This work identifies two…
Data mining, machine learning, and natural language processing are powerful techniques that can be used together to extract information from large texts. Depending on the task or problem at hand, there are many different approaches that can…
To acquire instruction-following capabilities, large language models (LLMs) undergo instruction tuning, where they are trained on instruction-response pairs using next-token prediction (NTP). Efforts to improve instruction tuning often…
In Large Language Model (LLM) fine-tuning, parameter and data selection are common strategies for reducing fine-tuning cost, yet they are typically driven by separate scoring mechanisms. When a parameter mask and data subset jointly…
Supervised fine-tuning (SFT) is a commonly used technique to adapt large language models (LLMs) to downstream tasks. In practice, SFT on a full dataset is computationally expensive and sometimes suffers from overfitting or bias…
How can we train models to perform well on hard test data when hard training data is by definition difficult to label correctly? This question has been termed the scalable oversight problem and has drawn increasing attention as language…
Large Language Models (LLMs) tend to prioritize adherence to user prompts over providing veracious responses, leading to the sycophancy issue. When challenged by users, LLMs tend to admit mistakes and provide inaccurate responses even if…
Large language models (LLMs) have been widely used for problem-solving tasks. Most recent work improves their performance through supervised fine-tuning (SFT) with labeled data or reinforcement learning (RL) from task feedback. In this…
Supervised fine-tuning (SFT) is a common approach to improve the domain-specific question-answering (QA) performance of large language models (LLMs). However, recent literature reveals that due to the conflicts between LLMs' internal…
Data is a critical asset for training large language models (LLMs), alongside compute resources and skilled workers. While some training data is publicly available, substantial investment is required to generate proprietary datasets, such…
Aligning the output of Large Language Models (LLMs) with human preferences (e.g., by means of reinforcement learning with human feedback, or RLHF) is essential for ensuring their effectiveness in real-world scenarios. Despite significant…
Supervised fine-tuning (SFT) is crucial in adapting large language model (LLMs) to a specific domain or task. However, only a limited amount of labeled data is available in practical applications, which poses a severe challenge for SFT in…