Reading
Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
Lewis, Perez, Piktus, et al. · 2020 · NeurIPS
rag
nlp
retrieval
Halfway through the experiments. Want to compare dense vs sparse retrieval claims.
Keep research papers organized — queue, reading progress, notes, and ratings in one calm place.
Lewis, Perez, Piktus, et al. · 2020 · NeurIPS
Halfway through the experiments. Want to compare dense vs sparse retrieval claims.
Brown, Mann, Ryder, et al. · 2020 · NeurIPS
Hu, Shen, Wallis, et al. · 2022 · ICLR
Practical PEFT baseline. Keep handy when choosing adapters vs full fine-tune.
Bai, Kadavath, Kundu, et al. · 2022 · arXiv
Parked after intro — revisit when working on preference learning.
Vaswani, Shazeer, Parmar, et al. · 2017 · NeurIPS
The transformer architecture paper. Self-attention replaces recurrence. Re-read the multi-head attention section.