conftrace_

token frequency

7 papers

Explore in graph

Co-occurring keywords

large language model (13587) language model (4599) data mixture (9) linear program (26) training data composition (2) long-tail distribution (80) membership inference (114) layer normalization (65) membership inference attack (93) pre-training datum (25)

Papers

Ranking Human and LLM Texts Using Locality Statistics EACL 2026

Long-Tail Crisis in Nearest Neighbor Language Models NAACL 2025

MiLe Loss: a New Loss for Mitigating the Bias of Learning Difficulties in Generative Language Models NAACL 2024

Data Mixture Inference Attack: BPE Tokenizers Reveal Training Data Compositions NIPS 2024

Confidence Regulation Neurons in Language Models NIPS 2024

Frequency Balanced Datasets Lead to Better Language Models EMNLP 2023

Token-level Adaptive Training for Neural Machine Translation EMNLP 2020