Stop letting LLMs edit your .bib [D]
Summary
The article criticizes the reliance on Large Language Models for generating bibliographic entries, highlighting issues with hallucinated citations and incorrect author lists in academic papers.
Similar Articles
Local LLM for legal-document adaptation keeps hallucinating citations with total confidence — grounding/model/pipeline ideas?
A user reports that a local LLM hallucinates citations with high confidence when adapted for legal documents, and seeks advice on grounding, model, or pipeline ideas to mitigate this issue.
The only ethical way to use LLMs for research is with a closed-loop LLM Knowledge Base.
The article argues that using LLMs for research requires a closed-loop system like Karpathy's LLM Wiki or the Recall AI knowledge base to prevent hallucinations, ensuring all outputs are grounded in trusted source documents.
Now Is the Time to Give LLMs Access to the ACM Digital Library
This article argues that the time is right to grant large language models (LLMs) access to the ACM Digital Library, balancing copyright concerns with the benefits of AI research and development.
Experts Rise Where LLMs Disagree: Using Cross-Model Disagreement to Target Expert Effort in LLM Codebook Revision for Large-Scale Annotation
The paper investigates using cross-model disagreement in LLMs to target expert effort in revising codebooks for large-scale text annotation, showing that rationale labeling outperforms other feedback methods.
Can LLMs realise we're looking at a problem the wrong way?
The article questions whether large language models can independently recognize and challenge foundational assumptions in science to achieve paradigm-shifting breakthroughs, drawing parallels to human innovations like Einstein's theory of gravity.