Yongil Kim

Seoul National University

Yongil's Research Blog

  1. [EMNLP2023] Enhancing Chat Language Models by Scaling High-quality Instructional Conversations » 17 Apr 2024
  2. [ICLR2024] #INSTAG: INSTRUCTION TAGGING FOR ANALYZING SUPERVISED FINE-TUNING OF LARGE LANGUAGE MODELS » 15 Apr 2024
  3. [Arxiv 2404]HyperCLOVA X Technical Report » 05 Apr 2024
  4. [ICLR2024] DP-OPT: MAKE LARGE LANGUAGE MODEL YOUR PRIVACY-PRESERVING PROMPT ENGINEER » 03 Apr 2024
  5. [ICLR2024] LOFTQ: LORA-FINE-TUNING-AWARE QUANTIZATION FOR LARGE LANGUAGE MODELS » 01 Apr 2024
  6. [Arxiv 2402] REAR: A Relevance-Aware Retrieval-Augmented Framework for Open-Domain Question Answering » 29 Mar 2024
  7. [EMNLP2023] EtiCor: Corpus for Analyzing LLMs for Etiquettes » 27 Mar 2024
  8. [EMNLP2023] Uncertainty Guided Global Memory Improves Multi-Hop Question » 25 Mar 2024
  9. [EMNLP2021 best paper] Visually Grounded Reasoning across Languages and Cultures » 22 Mar 2024
  10. [TACL2021] Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies » 20 Mar 2024
  11. [ACL2023] ReAugKD: Retrieval-Augmented Knowledge Distillation For Pre-trained Language Models » 18 Mar 2024
  12. [Arxiv 2305] Trusting Your Evidence: Hallucinate Less with Context-aware Decoding » 15 Mar 2024
  13. [Arxiv 2401] Blinded by Generated Contexts: How Language Models Merge Generated and Retrieved Contexts for Open-Domain QA? » 13 Mar 2024
  14. [EMNLP2023] IfQA: A Dataset for Open-domain Question Answeringunder Counterfactual Presuppositions » 11 Mar 2024
  15. [EMNLP2023] SMoP: Towards Efficient and Effective Prompt Tuning with Sparse Mixture-of-Prompts » 08 Mar 2024
  16. [EMNLP2023] Ditto: A Simple and Efficient Approach to Improve Sentence Embeddings » 06 Mar 2024
  17. [EMNLP2023] PK-ICR: Persona-Knowledge Interactive Multi-Context Retrieval for Grounded Dialogue » 04 Mar 2024
  18. [ACL2023] A Synthetic Data Generation Framework for Grounded Dialogues » 28 Feb 2024
  19. [EMNLP2023] CLAIR: Evaluating Image Captions with Large Language Models » 26 Feb 2024
  20. [EMNLP2023] TaskDiff: A Similarity Metric for Task-Oriented Conversations » 23 Feb 2024