A Comprehensive Survey of LLM Alignment Techniques: RLHF, RLAIF, PPO, DPO and More

With advancements in self-supervised learning, the availability of trillions tokens in a pre-training corpus, instruction fine-tuning, and the development of large Transformers with billions of parameters, large language models (LLMs) are now capable of generating factual and coherent responses to human queries. However, the mixed quality of training data can lead to the generation of undesired responses, presenting a significant challenge. Over the past two years, various methods have been proposed from different perspectives to enhance LLMs, particularly in aligning them with human expectation. Despite these efforts, there has not been a comprehensive survey paper that categorizes and details these approaches. In this work, we aim to address this gap by categorizing these papers into distinct topics and providing detailed explanations of each alignment method, thereby helping readers gain a thorough understanding of the current state of the field.

PAFT: A Parallel Training Paradigm for Effective LLM Fine-Tuning

Large language models (LLMs) have shown remarkable abilities in diverse natural language processing (NLP) tasks. The LLMs generally undergo supervised fine-tuning (SFT) followed by preference alignment to be usable in downstream applications. However, this sequential training pipeline leads to alignment tax that degrades the LLM performance. This paper introduces PAFT, a new PArallel training paradigm for effective LLM Fine-Tuning, which independently performs SFT and preference alignment (e.g., DPO and ORPO, etc.) with the same pre-trained model on respective datasets. The model produced by SFT and the model from preference alignment are then merged into a final model by parameter fusing for use in downstream applications. This work reveals important findings that preference alignment like DPO naturally results in a sparse model while SFT leads to a natural dense model which needs to be sparsified for effective model merging. This paper introduces an effective interference resolution which reduces the redundancy by sparsifying the delta parameters. The LLM resulted from the new training paradigm achieved Rank #1 on the HuggingFace Open LLM Leaderboard. Comprehensive evaluation shows the effectiveness of the parallel training paradigm.

Seeing is Knowing! Fact-based Visual Question Answering using Knowledge Graph Embeddings

Fact-based Visual Question Answering (FVQA), a challenging variant of VQA, requires a QA-system to include facts from a diverse knowledge graph (KG) in its reasoning process to produce an answer. Large KGs, especially common-sense KGs, are known to be incomplete, i.e. not all non-existent facts are always incorrect. Therefore, being able to reason over incomplete KGs for QA is a critical requirement in real-world applications that has not been addressed extensively in the literature. We develop a novel QA architecture that allows us to reason over incomplete KGs, something current FVQA state-of-the-art (SOTA) approaches lack.We use KG Embeddings, a technique widely used for KG completion, for the downstream task of FVQA. We also employ a new image representation technique we call "Image-as-Knowledge" to enable this capability, alongside a simple one-step co-Attention mechanism to attend to text and image during QA. Our FVQA architecture is faster during inference time, being O(m), as opposed to existing FVQA SOTA methods which are O(N logN), where m is number of vertices, N is number of edges (which is O(m^2)). We observe that our architecture performs comparably in the standard answer-retrieval baseline with existing methods; while for missing-edge reasoning, our KG representation outperforms the SOTA representation by 25%, and image representation outperforms the SOTA representation by 2.6%.