Pivotal Token Search

A Survey of Direct Preference Optimization (DPO)

Official Implementation (Pytorch) of the "VidChain: Chain-of-Tasks with Metric-based Direct Preference Optimization for Dense Video Captioning", AAAI 2025

[ICML 2025] TGDPO: Harnessing Token-Level Reward Guidance for Enhancing Direct Preference Optimization

A Comprehensive Survey of Direct Preference Optimization: Datasets, Theories, Variants, and Applications

Notebooks to create an instruction following version of Microsoft's Phi 2 LLM with Supervised Fine Tuning and Direct Preference Optimization (DPO)

RankPO: Rank Preference Optimization

The Rap Music Generator project is an innovative LLM-based tool designed to create rap lyrics. It offers multiple fine-tuning approaches to accommodate diverse rap generation techniques, providing users with a versatile platform for generating unique and stylistically varied content.

Evaluate how LLaMA 3.1 8B handles paraphrased adversarial prompts targeting refusal behavior.

Experiments, and how-to guide for the lecture "Large language models for Scientometrics"

Notebooks to create an instruction following version of Microsoft's Phi 1.5 LLM with Supervised Fine Tuning and Direct Preference Optimization (DPO)

[CC 2025] [Official code] - Engaging preference optimization alignment in large language model for continual radiology report generation: A hybrid approach

[ICML 2025 Workshop FM4BS] AnnoDPO: Protein Functional Annotation Learning with Direct Preference Optimization

EPFLLaMA: A lightweight language model fine-tuned on EPFL curriculum content. Specialized for STEM education and multiple-choice question answering. Implements advanced techniques like SFT, DPO, and quantization.

Enhancing paraphrase-type generation using Direct Preference Optimization (DPO) and Reinforcement Learning from Human Feedback (RLHF), with large-scale HPC support. This project aligns model outputs to human-ranked data for robust, safety-focused NLP.

EPFLLaMA: A lightweight language model fine-tuned on EPFL curriculum content. Specialized for STEM education and multiple-choice question answering. Implements advanced techniques like SFT, DPO, and quantization.