Related papers: Growing a Tail: Increasing Output Diversity in Lar…
This paper explores the advancements in making large language models (LLMs) more human-like. We focus on techniques that enhance natural language understanding, conversational coherence, and emotional intelligence in AI systems. The study…
We introduce {\em generative monoculture}, a behavior observed in large language models (LLMs) characterized by a significant narrowing of model output diversity relative to available training data for a given task: for example, generating…
As creative writing tasks do not have singular correct answers, large language models (LLMs) trained to perform these tasks should be able to generate diverse valid outputs. However, LLM post-training often focuses on improving generation…
Instruction-tuning large language models (LLMs) reduces the diversity of their outputs, which has implications for many tasks, particularly for creative tasks. This paper investigates the ``diversity gap'' for a writing prompt narrative…
How can large language models (LLMs) serve users with varying preferences that may conflict across cultural, political, or other dimensions? To advance this challenge, this paper establishes four key results. First, we demonstrate, through…
Technology for open-ended language generation, a key application of artificial intelligence, has advanced to a great extent in recent years. Large-scale language models, which are trained on large corpora of text, are being used in a wide…
Language models (LMs) have exhibited impressive abilities in generating code from natural language requirements. In this work, we highlight the diversity of code generated by LMs as a critical criterion for evaluating their code generation…
Access to large amounts of diverse design solutions can support designers during the early stage of the design process. In this paper, we explore the efficacy of large language models (LLM) in producing diverse design solutions,…
Inductive reasoning - the process of inferring general rules from a small number of observations - is a fundamental aspect of human intelligence. Recent works suggest that large language models (LLMs) can engage in inductive reasoning by…
The recent surge of generative AI has been fueled by the generative power of diffusion probabilistic models and the scalable capabilities of large language models. Despite their potential, it remains elusive whether diffusion language…
Large language models (LLMs) are trained on vast amounts of data to generate natural language, enabling them to perform tasks like text summarization and question answering. These models have become popular in artificial intelligence (AI)…
This paper investigates the voting behaviors of Large Language Models (LLMs), specifically GPT-4 and LLaMA-2, their biases, and how they align with human voting patterns. Our methodology involved using a dataset from a human voting…
Large language models (LLMs) have shown significant potential to change how we write, communicate, and create, leading to rapid adoption across society. This dissertation examines how individuals and institutions are adapting to and…
Large Language Models (LLMs) generate responses to questions; however, their effectiveness is often hindered by sub-optimal quality of answers and occasional failures to provide accurate responses to questions. To address these challenges,…
Response diversity has become an important criterion for evaluating the quality of open-domain dialogue generation models. However, current evaluation metrics for response diversity often fail to capture the semantic diversity of generated…
Large language models (LLMs) have been recently leveraged as training data generators for various natural language processing (NLP) tasks. While previous research has explored different approaches to training models using generated data,…
We carry out a series of experiments to test large language models' multi-hop reasoning ability from three aspects: selecting and combining external knowledge, dealing with non-sequential reasoning tasks and generalising to data samples…
Sampling-based decoding strategies have been widely adopted for Large Language Models (LLMs) in numerous applications, targeting a balance between diversity and quality via temperature tuning and tail truncation. Considering the strong…
Generative AI model outputs have been increasingly evaluated for their (in)ability to represent non-Western cultures. We argue that these evaluations often operate through reductive ideals of representation, abstracted from how people…
This paper presents a system for diversity-aware autonomous conversation leveraging the capabilities of large language models (LLMs). The system adapts to diverse populations and individuals, considering factors like background,…