相关论文: What Else Do I Need to Know? The Effect of Backgro…

The objective of this paper is to explore the opportunities for human information behaviour research to inform and influence the field of machine learning and the resulting machine information behaviour. Using the development of foundation…

Language models (LMs) often struggle to pay enough attention to the input context, and generate texts that are unfaithful or contain hallucinations. To mitigate this issue, we present context-aware decoding (CAD), which follows a…

Social contexts -- such as families, schools, and neighborhoods -- shape life outcomes. The key question is not simply whether they matter, but rather for whom and under what conditions. Here, we argue that prediction gaps -- differences in…

Current QA systems can generate reasonable-sounding yet false answers without explanation or evidence for the generated answer, which is especially problematic when humans cannot readily check the model's answers. This presents a challenge…

Artificial intelligence (AI) is increasingly being considered to assist human decision-making in high-stake domains (e.g. health). However, researchers have discussed an issue that humans can over-rely on wrong suggestions of the AI model…

Large language models (LLMs) generate outputs by utilizing extensive context, which often includes redundant information from prompts, retrieved passages, and interaction history. In critical applications, it is vital to identify which…

Training and refreshing a web-scale Question Answering (QA) system for a multi-lingual commercial search engine often requires a huge amount of training examples. One principled idea is to mine implicit relevance feedback from user behavior…

Retrieval-Augmented Language Models (RALMs) have significantly improved performance in open-domain question answering (QA) by leveraging external knowledge. However, RALMs still struggle with unanswerable queries, where the retrieved…

While large language models (LLMs) are increasingly used as automatic judges for question answering (QA) and other reference-conditioned evaluation tasks, little is known about their ability to adhere to a provided reference. We identify a…

Advances in deep learning systems have allowed large models to match or surpass human accuracy on a number of skills such as image classification, basic programming, and standardized test taking. As the performance of the most capable…

Large language models are being widely used across industries to generate content that contributes directly to key performance metrics, such as conversion rates. Pretrained models, however, often fall short when it comes to aligning with…

Modeling natural language inference is a very challenging task. With the availability of large annotated data, it has recently become feasible to train complex models such as neural-network-based inference models, which have shown to…

Large Language Models (LLMs) have been found to have difficulty knowing they do not possess certain knowledge and tend to provide specious answers in such cases. Retrieval Augmentation (RA) has been extensively studied to mitigate LLMs'…

Large language models (LLMs) often rely on outdated knowledge when answering time-sensitive questions, leading to confident yet incorrect responses. Without explicit signals indicating whether up-to-date information is required, models…

A common use of NLP is to facilitate the understanding of large document collections, with a shift from using traditional topic models to Large Language Models. Yet the effectiveness of using LLM for large corpus understanding in real-world…

Deep learning technologies have brought us many models that outperform human beings on a few benchmarks. An interesting question is: can these models well solve real-world problems with similar settings (e.g., identical input/output) to the…

Large language models (LLMs) increasingly operate in environments where they encounter social information such as other agents' answers, tool outputs, or human recommendations. In humans, such inputs influence judgments in ways that depend…

Large language models (LLMs) have shown impressive prowess in solving a wide range of tasks with world knowledge. However, it remains unclear how well LLMs are able to perceive their factual knowledge boundaries, particularly under…

Recent advances in the development of large language models are rapidly changing how online applications function. LLM-based search tools, for instance, offer a natural language interface that can accommodate complex queries and provide…

An implicit expectation of asking users to rate agents, such as an AI decision-aid, is that they will use only relevant information -- ask them about an agent's benevolence, and they should consider whether or not it was kind. Behavioral…