Related papers: Weak-to-Strong Generalization: Eliciting Strong Ca…

Language models have seen significant growth in the size of their corpus, leading to notable performance improvements. Yet, there has been limited progress in developing models that handle smaller, more human-like datasets. As part of the…

Steering the behavior of a strong model pre-trained on internet-scale data can be difficult due to the scarcity of competent supervisors. Recent studies reveal that, despite supervisory noises, a strong student model may surpass its weak…

Reinforcement Learning from Human Feedback (RLHF) facilitates the alignment of large language models with human preferences, significantly enhancing the quality of interactions between humans and models. InstructGPT implements RLHF through…

Neural ranking models (NRMs) have demonstrated effective performance in several information retrieval (IR) tasks. However, training NRMs often requires large-scale training data, which is difficult and expensive to obtain. To address this…

Large language models are usually fine-tuned to align with human preferences. However, fine-tuning a large language model can be challenging. In this work, we introduce $\textit{weak-to-strong search}$, framing the alignment of a large…

Recent advancements in natural language processing by large language models (LLMs), such as GPT-4, have been suggested to approach Artificial General Intelligence. And yet, it is still under dispute whether LLMs possess similar reasoning…

Language model (LM) post-training relies on two stages of human supervision: task demonstrations for supervised finetuning (SFT), followed by preference comparisons for reinforcement learning from human feedback (RLHF). As LMs become more…

State-of-the-art large language models (LLMs) have become indispensable tools for various tasks. However, training LLMs to serve as effective assistants for humans requires careful consideration. A promising approach is reinforcement…

We apply preference modeling and reinforcement learning from human feedback (RLHF) to finetune language models to act as helpful and harmless assistants. We find this alignment training improves performance on almost all NLP evaluations,…

Neural network approaches have recently shown to be effective in several information retrieval (IR) tasks. However, neural approaches often require large volumes of training data to perform effectively, which is not always available. To…

As AI systems begin to automate complex tasks, supervision increasingly relies on weaker models or limited human oversight that cannot fully verify output quality. A model more capable than its supervisors could exploit this gap through…

The burgeoning capabilities of large language models (LLMs) have underscored the need for alignment to ensure these models act in accordance with human values and intentions. Existing alignment frameworks present constraints either in the…

This paper studies reinforcement learning from human feedback (RLHF) for aligning large language models with human preferences. While RLHF has demonstrated promising results, many algorithms are highly sensitive to misspecifications in the…

As large language models (LLMs) have increased in their capabilities, so does their potential for dual use. To reduce harmful outputs, produces and vendors of LLMs have used reinforcement learning with human feedback (RLHF). In tandem, LLM…

Reinforcement learning (RL) is a powerful framework for learning to take actions to solve tasks. However, in many settings, an agent must winnow down the inconceivably large space of all possible tasks to the single task that it is…

When large language models (LLMs) exceed human-level capabilities, it becomes increasingly challenging to provide full-scale and accurate supervision for these models. Weak-to-strong learning, which leverages a less capable model to unlock…

Learning from human feedback is a prominent technique to align the output of large language models (LLMs) with human expectations. Reinforcement learning from human feedback (RLHF) leverages human preference signals that are in the form of…

Large language models (LLMs) trained via pretraining and supervised fine-tuning (SFT) can still produce harmful and misaligned outputs, or struggle in domains like math and coding. Reinforcement learning (RL)-based post-training methods,…

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…

Recent strides in large language models (LLMs) have yielded remarkable performance, leveraging reinforcement learning from human feedback (RLHF) to significantly enhance generation and alignment capabilities. However, RLHF encounters…