Related papers: Natural Language Fine-Tuning
Large language models (LLMs) have achieved remarkable progress in reasoning tasks, yet the optimal integration of Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) remains a fundamental challenge. Through comprehensive analysis…
Supervised Fine-Tuning (SFT) is essential for training large language models (LLMs), significantly enhancing critical capabilities such as instruction following and in-context learning. Nevertheless, creating suitable training datasets…
Large Language Models (LLMs) are typically fine-tuned for reasoning tasks through a two-stage pipeline of Supervised Fine-Tuning (SFT) followed by Reinforcement Learning (RL), a process fraught with catastrophic forgetting and suboptimal…
Large language models (LLMs), owing to their extensive open-domain knowledge and semantic reasoning capabilities, have been increasingly integrated into recommender systems (RS). However, a substantial gap remains between the pre-training…
Modern instruction-tuned large language models (LLMs) have made remarkable progress in code generation. However, these LLMs fine-tuned with standard supervised fine-tuning (SFT) sometimes generate plausible-looking but functionally…
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,…
Despite the effectiveness of data selection for large language models (LLMs) during pretraining and instruction fine-tuning phases, improving data efficiency in supervised fine-tuning (SFT) for specialized domains poses significant…
This paper presents a study on strategies to enhance the translation capabilities of large language models (LLMs) in the context of machine translation (MT) tasks. The paper proposes a novel paradigm consisting of three stages: Secondary…
Pre-trained large-scale language models (LLMs) excel at producing coherent articles, yet their outputs may be untruthful, toxic, or fail to align with user expectations. Current approaches focus on using reinforcement learning with human…
Motivation: A perennial challenge for biomedical researchers and clinical practitioners is to stay abreast with the rapid growth of publications and medical notes. Natural language processing (NLP) has emerged as a promising direction for…
Multimodal large language models (MLLMs) fine-tuned with multimodal instruction datasets have demonstrated remarkable capabilities in multimodal tasks. However, fine-tuning all parameters of MLLMs has become challenging as they usually…
Large language models (LLMs) with enormous pre-training tokens and parameters emerge diverse abilities, including math reasoning, code generation, and instruction following. These abilities are further enhanced by supervised fine-tuning…
The adaptation of large language models (LLMs) to specialized reasoning tasks is fundamentally constrained by computational resources. Parameter-Efficient Fine-Tuning (PEFT) methods have emerged as a powerful solution, yet the landscape of…
The prevailing paradigm for training large reasoning models--combining Supervised Fine-Tuning (SFT) with Reinforcement Learning with Verifiable Rewards (RLVR)--is fundamentally constrained by its reliance on high-quality, human-annotated…
Large Language Models are expressive tools that enable complex tasks of text understanding within Computational Social Science. Their versatility, while beneficial, poses a barrier for establishing standardized best practices within the…
Large language models (LLMs) with billions of parameters and pretrained on massive amounts of data are now capable of near or better than state-of-the-art performance in a variety of downstream natural language processing tasks. Neural…
Value-based reinforcement learning (RL) can in principle learn effective policies for a wide range of multi-turn problems, from games to dialogue to robotic control, including via offline RL from static previously collected datasets.…
Translating natural language (NL) into a formal language such as temporal logic (TL) is integral for human communication with robots and autonomous systems. State-of-the-art approaches decompose the task into a lifting of atomic…
While supervised fine-tuning (SFT) has been a straightforward approach for tailoring the output of foundation large language model (LLM) to specific preferences, concerns have been raised about the depth of this alignment, with some…
Current LLM-based services typically require users to submit raw text regardless of its sensitivity. While intuitive, such practice introduces substantial privacy risks, as unauthorized access may expose personal, medical, or legal…