Related papers: Intuitive Fine-Tuning: Towards Simplifying Alignme…

Direct Preference Optimization (DPO) has recently emerged as a popular approach to improve reinforcement learning with human feedback (RLHF), leading to better techniques to fine-tune large language models (LLM). A weakness of DPO, however,…

Current multimodal large language models (MLLMs) struggle with fine-grained or precise understanding of visuals although they give comprehensive perception and reasoning in a spectrum of vision applications. Recent studies either develop…

A common technique for aligning large language models (LLMs) relies on acquiring human preferences by comparing multiple generations conditioned on a fixed context. This method, however, relies solely on pairwise comparisons, where the…

The rapid advancement of large language models (LLMs) has facilitated their transformation into conversational chatbots that can grasp contextual nuances and generate pertinent sentences, closely mirroring human values through advanced…

While large language models demonstrate remarkable capabilities, they often present challenges in terms of safety, alignment with human values, and stability during training. Here, we focus on two prevalent methods used to align these…

Iterative preference optimization methods have recently been shown to perform well for general instruction tuning tasks, but typically make little improvement on reasoning tasks (Yuan et al., 2024, Chen et al., 2024). In this work we…

Prompt tuning (PT) is an effective approach to adapting pre-trained language models to downstream tasks. Without a good initialization, prompt tuning doesn't perform well under few-shot settings. So pre-trained prompt tuning (PPT) is…

The alignment of large language models (LLMs) with human preferences remains a key challenge. While post-training techniques like Reinforcement Learning from Human Feedback (RLHF) and Direct Preference Optimization (DPO) have achieved…

Supervised fine-tuning (SFT) plays a critical role for pretrained large language models (LLMs), notably enhancing their capacity to acquire domain-specific knowledge while preserving or potentially augmenting their general-purpose…

Personalisation is a standard feature of conversational AI systems used by millions; yet, the efficacy of personalisation methods is often evaluated in academic research using simulated users rather than real people. This raises questions…

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…

The quality of human preference data is crucial for training and evaluating large language models (LLMs), particularly in reinforcement learning from human feedback (RLHF) and direct preference optimization (DPO) scenarios. Traditional…

Mathematical reasoning presents a significant challenge for Large Language Models (LLMs) due to the extensive and precise chain of reasoning required for accuracy. Ensuring the correctness of each reasoning step is critical. To address…

Supervised fine-tuning (SFT), supervised instruction tuning (SIT) and in-context learning (ICL) are three alternative, de facto standard approaches to few-shot learning. ICL has gained popularity recently with the advent of LLMs due to its…

Advancements in Large Language Models (LLMs) have significantly enhanced instruction-following capabilities. However, most Instruction Fine-Tuning (IFT) datasets are predominantly in English, limiting model performance in other languages.…

Supervised fine-tuning (SFT) is crucial for adapting Large Language Models (LLMs) to specific tasks. In this work, we demonstrate that the order of training data can lead to significant training imbalances, potentially resulting in…

With the continuous growth in the number of parameters of transformer-based pretrained language models (PLMs), particularly the emergence of large language models (LLMs) with billions of parameters, many natural language processing (NLP)…

Evaluating preference optimization (PO) algorithms on LLM alignment is a challenging task that presents prohibitive costs, noise, and several variables like model size and hyper-parameters. In this work, we show that it is possible to gain…

Large Language Models (LLMs) show strong reasoning abilities, often amplified by Chain-of-Thought (CoT) prompting and reinforcement learning (RL). Although RL algorithms can substantially improve reasoning, they struggle to expand reasoning…

Recent advances in large language models have demonstrated that Supervised Fine-Tuning (SFT) with Chain-of-Thought (CoT) reasoning data distilled from large reasoning models (e.g., DeepSeek R1) can effectively transfer reasoning…