Related papers: AlignTune: Modular Toolkit for Post-Training Align…

Fine-tuning pretrained language models (PLMs) on downstream tasks has become common practice in natural language processing. However, most of the PLMs are vulnerable, e.g., they are brittle under adversarial attacks or imbalanced data,…

Alignment training is crucial for enabling large language models (LLMs) to cater to human intentions and preferences. It is typically performed based on two stages with different objectives: instruction-following alignment and…

Aligning large language models (LLMs) to human values has become increasingly important as it enables sophisticated steering of LLMs. However, it requires significant human demonstrations and feedback or distillation from proprietary LLMs…

Due to the remarkable capabilities and growing impact of large language models (LLMs), they have been deeply integrated into many aspects of society. Thus, ensuring their alignment with human values and intentions has emerged as a critical…

The development of large language models leads to the formation of a pre-train-then-align paradigm, in which the model is typically pre-trained on a large text corpus and undergoes a tuning stage to align the model with human preference or…

Foundation models have demonstrated a great ability to achieve general human-level intelligence far beyond traditional approaches. As the technique keeps attracting attention from the AI community, an increasing number of foundation models…

Large language models (LLMs) have shown tremendous success in following user instructions and generating helpful responses. Nevertheless, their robustness is still far from optimal, as they may generate significantly inconsistent responses…

Large Language Models (LLMs) are nowadays expected to generate content aligned with human preferences. Current work focuses on alignment at model training time, through techniques such as Reinforcement Learning with Human Feedback (RLHF).…

Supervised fine-tuning (SFT) is a critical step in aligning large language models (LLMs) with human instructions and values, yet many aspects of SFT remain poorly understood. We trained a wide range of base models on a variety of datasets…

From the perspective of content safety issues, alignment has shown to limit large language models' (LLMs) harmful content generation. This intentional method of reinforcing models to not respond to certain user inputs seem to be present in…

Despite their powerful text generation capabilities, large language models (LLMs) still struggle to effectively utilize external tools to solve complex tasks, a challenge known as tool learning. Existing methods primarily rely on supervised…

Large language models (LLMs) are increasingly being used as decision aids. However, users have diverse values and preferences that can affect their decision-making, which requires novel methods for LLM alignment and personalization.…

We propose a novel reinforcement learning framework for post training large language models that does not rely on human in the loop feedback. Instead, our approach uses cross attention signals within the model itself to derive a self…

Due to limited supervised training data, large language models (LLMs) are typically pre-trained via a self-supervised "predict the next word" objective on a vast amount of unstructured text data. To make the resulting model useful to users,…

Large Language Models (LLMs) demonstrate transformative potential, yet their reasoning remains inconsistent and unreliable. Reinforcement learning (RL)-based fine-tuning is a key mechanism for improvement, but its effectiveness is…

As large language models (LLMs) are trained on massive datasets, they have raised significant privacy and ethical concerns due to their potential to inadvertently retain sensitive information. Unlearning seeks to selectively remove specific…

Reward design plays a pivotal role in aligning large language models (LLMs) with human values, serving as the bridge between feedback signals and model optimization. This survey provides a structured organization of reward modeling and…

Model alignment with human preferences is an essential step in making Large Language Models (LLMs) helpful and consistent with human values. It typically consists of supervised fine-tuning (SFT) and reinforcement learning from human…

Standard training pipelines for large language models (LLMs) are typically unidirectional, progressing from pre-training to post-training. However, the potential for a bidirectional process--where insights from post-training retroactively…

Large Language Models (LLMs) have demonstrated remarkable capabilities and have been extensively deployed across various domains, including recommender systems. Prior research has employed specialized \textit{prompts} to leverage the…