Related papers: InstructPatentGPT: Training patent language models…

Advances in perception modeling have significantly improved the performance of object tracking. However, the current methods for specifying the target object in the initial frame are either by 1) using a box or mask template, or by 2)…

Reinforcement learning from human feedback usually models preferences using a reward function that does not distinguish between people. We argue that this is unlikely to be a good design choice in contexts with high potential for…

With the development of AI-Generated Content (AIGC), text-to-audio models are gaining widespread attention. However, it is challenging for these models to generate audio aligned with human preference due to the inherent information density…

The recently released ChatGPT has demonstrated surprising abilities in natural language understanding and natural language generation. Machine translation relies heavily on the abilities of language understanding and generation. Thus, in…

Much literature has shown that prompt-based learning is an efficient method to make use of the large pre-trained language model. Recent works also exhibit the possibility of steering a chatbot's output by plugging in an appropriate prompt.…

Off-the-shelf natural language processing software performs poorly when parsing patent claims owing to their use of irregular language relative to the corpora built from news articles and the web typically utilized to train this software.…

Learning from human feedback has gained traction in fields like robotics and natural language processing in recent years. While prior works mostly rely on human feedback in the form of comparisons, language is a preferable modality that…

Many promising-looking ideas in AI research fail to deliver, but their validation takes substantial human labor and compute. Predicting an idea's chance of success is thus crucial for accelerating empirical AI research, a skill that even…

Recent advances in large-scale pre-training such as GPT-3 allow seemingly high quality text to be generated from a given prompt. However, such generation systems often suffer from problems of hallucinated facts, and are not inherently…

Patent examiners need to solve a complex information retrieval task when they assess the novelty and inventive step of claims made in a patent application. Given a claim, they search for prior art, which comprises all relevant publicly…

Large-scale pre-trained language models have demonstrated strong capabilities of generating realistic text. However, it remains challenging to control the generation results. Previous approaches such as prompting are far from sufficient,…

Text is a vehicle to convey information that reflects the writer's linguistic style and communicative patterns. By studying these attributes, we can discover latent insights about the author and their underlying message. This article uses…

Incorporating automatically predicted human feedback into the process of training generative models has attracted substantial recent interest, while feedback at inference time has received less attention. The typical feedback at training…

Given a patent document, identifying distinct semantic annotations is an interesting research aspect. Text annotation helps the patent practitioners such as examiners and patent attorneys to quickly identify the key arguments of any…

Deep generative models have shown impressive results in text-to-image synthesis. However, current text-to-image models often generate images that are inadequately aligned with text prompts. We propose a fine-tuning method for aligning such…

Reinforcement Learning from Human Feedback (RLHF) has become a crucial technology for aligning language models with human values and intentions, enabling models to produce more helpful and harmless responses. Reward models are trained as…

We propose a method to capture the handling abilities of fast jet pilots in a software model via reinforcement learning (RL) from human preference feedback. We use pairwise preferences over simulated flight trajectories to learn an…

PatentTransformer is our codename for patent text generation based on Transformer-based models. Our goal is "Augmented Inventing." In this second version, we leverage more of the structural metadata in patents. The structural metadata…

Reinforcement learning from human feedback (RLHF) has emerged as an effective approach to aligning large language models (LLMs) to human preferences. RLHF contains three steps, i.e., human preference collecting, reward learning, and policy…

Language model-based instruction-following systems have lately shown increasing performance on many benchmark tasks, demonstrating the capability of adapting to a broad variety of instructions. However, such systems are often not designed…