Direct Preference Optimisation (DPO) is effective at significantly improving the performance
of large language models (LLMs) on downstream tasks such as reasoning, summarisation …

In the field of large language models (LLMs), aligning models with the diverse preferences
of users is a critical challenge. Direct Preference Optimization (DPO) has played a key role …

One way to enhance the reasoning capability of Large Language Models (LLMs) is to
conduct Supervised Fine-Tuning (SFT) using Chain-of-Thought (CoT) annotations. This …

Direct Preference Optimization (DPO), which derives reward signals directly from pairwise
preference data, has shown its effectiveness on aligning Large Language Models (LLMs) …

As Large Language Models (LLMs) and Retrieval Augmentation Generation (RAG)
techniques have evolved, query rewriting has been widely incorporated into the RAG system …

The Socratic method is a way of guiding students toward solving a problem independently
without directly revealing the solution to the problem. Although this method has been shown …

Recent advances in large language models (LLMs) have led to their extensive global
deployment, and ensuring their safety calls for comprehensive and multilingual toxicity …

Current LLM alignment techniques use pairwise human preferences at a sample level, and
as such, they do not imply an alignment on the distributional level. We propose in this paper …

This paper addresses the challenges of aligning large language models (LLMs) with human
values via preference learning (PL), with a focus on the issues of incomplete and corrupted …

Foundation models such as GPT-4 are fine-tuned to avoid unsafe or otherwise problematic
behavior, such as helping to commit crimes or producing racist text. One approach to fine …