相关论文: Growing a Tail: Increasing Output Diversity in Lar…

The NLP research community has devoted increased attention to languages beyond English, resulting in considerable improvements for multilingual NLP. However, these improvements only apply to a small subset of the world's languages. Aiming…

Effectively leveraging diversity has been shown to improve performance for various machine learning models, including large language models (LLMs). However, determining the most effective way of using diversity remains a challenge. In this…

With the advance of Artificial Intelligence (AI), Large Language Models (LLMs) have gained prominence and been applied in diverse contexts. As they evolve into more sophisticated versions, it is essential to assess whether they reproduce…

Machine learning techniques have conquered many different tasks in speech and natural language processing, such as speech recognition, information extraction, text and speech generation, and human machine interaction using natural language…

Do generative AI models, particularly large language models (LLMs), exhibit systematic behavioral biases in economic and financial decisions? If so, how can these biases be mitigated? Drawing on the cognitive psychology and experimental…

This study provides the first comprehensive assessment of consistency and reproducibility in Large Language Model (LLM) outputs in finance and accounting research. We evaluate how consistently LLMs produce outputs given identical inputs…

Large language models have recently demonstrated remarkable abilities to self-correct their responses through iterative refinement, often referred to as self-consistency or self-reflection. However, the dynamics of this self-correction…

Learning from human feedback has become a pivot technique in aligning large language models (LLMs) with human preferences. However, acquiring vast and premium human feedback is bottlenecked by time, labor, and human capability, resulting in…

While Large Language Models (LLMs) have made significant strides in replicating human-like abilities, there are concerns about a reduction in the linguistic diversity of their outputs. This results in the homogenization of viewpoints and…

In this provocation, we discuss the English dominance of the AI research community, arguing that the requirement for English language publishing upholds and reinforces broader regimes of extraction in AI. While large language models and…

LLMs are not generally able to adjust the length of their outputs based on strict length requirements, a capability that would improve their usefulness in applications that require adherence to diverse user and system requirements. We…

Neural language models often fail to generate diverse and informative texts, limiting their applicability in real-world problems. While previous approaches have proposed to address these issues by identifying and penalizing undesirable…

Language Models have ushered a new age of AI gaining traction within the NLP community as well as amongst the general population. AI's ability to make predictions, generations and its applications in sensitive decision-making scenarios,…

Large language models often generate homogeneous outputs, but whether this is problematic depends on the specific task. For objective math tasks, responses may vary in terms of problem-solving strategy but should maintain the same…

Exposure to large language model output is rapidly increasing. How will seeing AI-generated ideas affect human ideas? We conducted an experiment (800+ participants, 40+ countries) where participants viewed creative ideas that were from…

Large language models (LLMs), especially when instruction-tuned for chat, have become part of our daily lives, freeing people from the process of searching, extracting, and integrating information from multiple sources by offering a…

There are both benefits and drawbacks to cultural diversity. It can lead to friction and exacerbate differences. However, as with biological diversity, cultural diversity is valuable in times of upheaval; if a previously effective solution…

All AI models are susceptible to learning biases in data that they are trained on. For generative dialogue models, being trained on real human conversations containing unbalanced gender and race/ethnicity references can lead to models that…

Back translation is one of the most widely used methods for improving the performance of neural machine translation systems. Recent research has sought to enhance the effectiveness of this method by increasing the 'diversity' of the…

Large language model behavior is shaped by the language of those with whom they interact. This capacity and their increasing prevalence online portend that they will intentionally or unintentionally "program" one another and form emergent…