_index.org

ACL2025 Li: TokAlign Token Alignment

Last edited: August 8, 2025

Method to adapt tokenization across models.

Notable Methods

  1. use pairwise cosine similarity between token embeddings to create a grid of alignment
  2. initialize new adapted embeddings for each id’s most similar tokens
  3. tune

ACL2025 Monday Morning Posters

Last edited: August 8, 2025

ACL2025 Zhang: FaithfulRAG: Fact level conflict modeling

Key insight: RAG performance degrades wen model has context and parametric knowledge mismatch, identifying those and use three step iterative method to improve context faithfulness.

ACL2025 Ding: LLM reasoning capability via scalable question synthesis

Key insight: generate free-from questions conditioned only in BOS, then distill and DPO to get a nice question generation dataset and directly fine tune

ACL2025 Wen: synthetic data strategy on domain specific retrieval

Key insight: train your models enough to memorize the context of a specific domain and therefore be able to recall better in particular using document based IDs

ACL2025 Orals: Efficient NLP

Last edited: August 8, 2025