# LG AI Research — KorQuAD 2.0 1st rank: Generative Model for Long Context Question Answering

- Company: LG AI Research (lgresearch.ai)
- Announced: 2023-12-19
- Category: not stated
- Coverage: not counted
- Announcement: no
- Group: routine
- Source: https://www.lgresearch.ai/blog/view?seq=374
- Record: https://forck.live/items/4881-korquad-2-0-1st-rank-generative-model-for-long-context-question-answering
- Subject: EXAONE
- Models affected: EXAONE LM 1.0

LG AI Research achieved 1st rank on the Korean machine reading comprehension benchmark KorQuAD 2.0 using their in-house developed EXAONE LM 1.0 model, employing post-training techniques (QA, HTML-T5) to handle HTML documents and long contexts.

## Evidence

Verbatim from https://www.lgresearch.ai/blog/view?seq=374:

> We challenged the leaderboard to showcase the excellent performance of our in-house developed EXAONE and recently achieved 1st rank of KorQuAD2.0

---

Record: https://forck.live/items/4881-korquad-2-0-1st-rank-generative-model-for-long-context-question-answering
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md