Related papers: Epistemic Diversity and Knowledge Collapse in Larg…
How does the natural evolution of context paragraphs affect question answering in generative Large Language Models (LLMs)? To investigate this, we propose a framework for curating naturally evolved, human-edited variants of reading passages…
Large Language Models (LLMs) that undergo recursive training on synthetically generated data are susceptible to model collapse, a phenomenon marked by the generation of meaningless output. Existing research has examined this issue from…
Large Language Models (LLMs), such as ChatGPT, are reshaping content creation and academic writing. This study investigates the impact of AI-assisted generative revisions on research manuscripts, focusing on heterogeneous adoption patterns…
Significant scientific discoveries have driven the progress of human civilisation. The explosion of scientific literature and data has created information barriers across disciplines that have slowed the pace of scientific discovery. Large…
Large Language Models (LLMs) are known for their remarkable ability to generate synthesized 'knowledge', such as text documents, music, images, etc. However, there is a huge gap between LLM's and human capabilities for understanding…
Citation practices are crucial in shaping the structure of scientific knowledge, yet they are often influenced by contemporary norms and biases. The emergence of Large Language Models (LLMs) introduces a new dynamic to these practices.…
Large language models (LLMs) show early signs of artificial general intelligence but struggle with hallucinations. One promising solution to mitigate these hallucinations is to store external knowledge as embeddings, aiding LLMs in…
Retrieval-augmented generation (RAG) mitigates many problems of fully parametric language models, such as temporal degradation, hallucinations, and lack of grounding. In RAG, the model's knowledge can be updated from documents provided in…
Context. Large Language Models (LLMs) are increasingly embedded in software engineering workflows for tasks including code generation, summarization, repair, and testing. Empirical studies report productivity gains, improved comprehension,…
Given varying prompts regarding a factoid question, can a large language model (LLM) reliably generate factually correct answers? Existing LLMs may generate distinct responses for different prompts. In this paper, we study the problem of…
Large Language Models (LLMs) are prone to generating fluent but incorrect content, known as confabulation, which poses increasing risks in multi-turn or agentic applications where outputs may be reused as context. In this work, we…
While hallucinations of large language models (LLMs) prevail as a major challenge, existing evaluation benchmarks on factuality do not cover the diverse domains of knowledge that the real-world users of LLMs seek information about. To…
The practice of Retrieval-Augmented Generation (RAG), which integrates Large Language Models (LLMs) with retrieval systems, has become increasingly prevalent. However, the repercussions of LLM-derived content infiltrating the web and…
Large language models (LLMs) acquire knowledge across diverse domains such as science, history, and geography encountered during generative pre-training. However, due to their stochasticity, it is difficult to predict what LLMs have…
The development and evaluation of Large Language Models (LLMs) has primarily focused on their task-solving capabilities, with recent models even surpassing human performance in some areas. However, this focus often neglects whether…
Large language models (LLMs) have transformed natural language processing, achieving remarkable performance across diverse tasks. However, their impressive fluency often comes at the cost of producing false or fabricated information, a…
Ideas generated by independent samples of humans tend to be more diverse than ideas generated from independent LLM samples, raising concerns that widespread reliance on LLMs could homogenize ideation and undermine innovation at a societal…
Model distillation is a fundamental technique in building large language models (LLMs), transferring knowledge from a teacher model to a student model. However, distillation can lead to model homogenization, reducing diversity among models…
The rise of generative large language models (LLMs) has opened new opportunities for automating knowledge representation through concept maps, a long-standing pedagogical tool valued for fostering meaningful learning and higher-order…
The development of highly fluent large language models (LLMs) has prompted increased interest in assessing their reasoning and problem-solving capabilities. We investigate whether several LLMs can solve a classic type of deductive reasoning…