Welcome to the HUMANE Lab 😎

๐Ÿ”ฅ (2024/11/27) ํ•™๋ถ€ ์—ฐ๊ตฌ์ƒ์„ ๋ชจ์ง‘ํ•˜๊ณ  ์žˆ์Šต๋‹ˆ๋‹ค. [Link] ๐Ÿ”ฅ

Human-Centered Language & Information Technologies (HUMANE) Lab at Soongsil University studies NLP and multimodal technologies based on large language models. Our research aims to tackle social problems in online platforms (e.g., misinformation, hate speech, bias) by developing learning and inference methods centered around human values.

์ˆญ์‹ค๋Œ€ํ•™๊ต ์ธ๊ฐ„-์ค‘์‹ฌ ์–ธ์–ด ๋ฐ ์ •๋ณด ๊ธฐ์ˆ  (ํœด๋ฉ”์ธ) ๋žฉ์€ ๋Œ€๊ทœ๋ชจ ์–ธ์–ด ๋ชจ๋ธ ๊ธฐ๋ฐ˜์˜ ์ž์—ฐ์–ด์ฒ˜๋ฆฌ ๋ฐ ๋ฉ€ํ‹ฐ๋ชจ๋‹ฌ ์ธ๊ณต์ง€๋Šฅ ๊ธฐ์ˆ ์„ ์—ฐ๊ตฌํ•ฉ๋‹ˆ๋‹ค. ์‚ฌ๋žŒ ๊ฐ€์น˜ ์ค‘์‹ฌ์˜ ํ•™์Šต ๋ฐ ์ถ”๋ก  ๋ฐฉ๋ฒ•์„ ๊ฐœ๋ฐœํ•˜์—ฌ ์˜จ๋ผ์ธ ํ”Œ๋žซํผ์—์„œ ๋‚˜ํƒ€๋‚˜๋Š” ์‚ฌ๋žŒ๊ณผ ์‚ฌํšŒ์— ๊ด€๋ จ๋œ ๋ฌธ์ œ(์˜ˆ. ์˜ค์ •๋ณด, ํ˜์˜ค, ํŽธํ–ฅ)๋ฅผ ํ•ด๊ฒฐํ•˜๋Š” ๊ฒƒ์„ ๋ชฉํ‘œํ•ฉ๋‹ˆ๋‹ค.

์„ฑ๊ณผ

  • ๊ตญ์ œ ์ €๋ช… ํ•™์ˆ ๋Œ€ํšŒ ๋…ผ๋ฌธ ๋ฐœํ‘œ: ACL, EMNLP ๋“ฑ
  • ๋…ผ๋ฌธ์ƒ ์ˆ˜์ƒ: ํ•œ๊ตญ์ธ๊ณต์ง€๋Šฅํ•™ํšŒ ์ตœ์šฐ์ˆ˜๋…ผ๋ฌธ์ƒ, ํ•œ๊ตญ์ •๋ณด๊ณผํ•™ํšŒ ์šฐ์ˆ˜๋…ผ๋ฌธ์ƒ ๋“ฑ
  • ๊ฒฝ์ง„๋Œ€ํšŒ ์ˆ˜์ƒ: ์„ธ๊ณ„ ์ธ๊ณต์ง€๋Šฅ ํŒฉํŠธ์ฒดํ‚น ๋Œ€ํšŒ 2์œ„ (co-located with EMNLP 2024)

์–ธ๋ก  ๋ณด๋„

  • ์ˆญ์‹ค๋Œ€ AI์œตํ•ฉํ•™๋ถ€ ๋ฐ•๊ฑด์šฐ ๊ต์ˆ˜ ์—ฐ๊ตฌํŒ€, ์ž๋™ํ™” ํŒฉํŠธ์ฒดํ‚น ๊ตญ์ œ๋Œ€ํšŒ์—์„œ 2์œ„ ์ฐจ์ง€ (ํ•œ๊ฒจ๋ก€ ๋“ฑ)
  • ์นด์นด์˜ค, โ€˜๊ณต๊ณต์„  ํฌ๋Ÿผโ€™์„œ ์‚ฌํšŒ ๋ฌธ์ œ ํ•ด๊ฒฐ ์œ„ํ•œ ํ”Œ๋žซํผ ๊ธฐ์—… ์—ญํ•  ๊ฐ•์กฐ (๋‰ด์‹œ์Šค)
  • ํŠœ๋‹™-์ˆญ์‹ค๋Œ€ ๊ณต๋™ ์—ฐ๊ตฌํŒ€, EMNLP 2023 ํŒŒ์ธ๋”ฉ์Šค์— ๋…ผ๋ฌธ ๊ฒŒ์žฌ (IT Daily)
  • ์ˆญ์‹ค๋Œ€ ์œค์˜ˆ์ค€ ํ•™๋ถ€์ƒ, 2023 ํ•œ๊ตญ์ธ๊ณต์ง€๋Šฅํ•™ํšŒ ํ•˜๊ณ„ํ•™์ˆ ๋Œ€ํšŒ ํ˜„๋Œ€์ž๋™์ฐจ ์ตœ์šฐ์ˆ˜๋…ผ๋ฌธ์ƒ ์ˆ˜์ƒ (์กฐ์„ ์ผ๋ณด)
  • [Qํ”Œ๋Ÿฌ์Šค] AI๊ฐ€ ๊ธฐ์‚ฌ ์“ฐ๊ณ  ํŒฉํŠธ์ฒดํฌ๊นŒ์ง€โ€ฆ๊ธฐ์ž๋Š” ์‚ฌ๋ผ์งˆ๊นŒ? (KBS)

Funding

  • IITP ์ •๋ณดํ†ต์‹ ๋ฐฉ์†กํ˜์‹ ์ธ์žฌ์–‘์„ฑ ์ง€์—ญ์ง€๋Šฅํ™”ํ˜์‹ ์ธ์žฌ์–‘์„ฑ (์„ธ๋ถ€์ฑ…์ž„)
  • NRF 4๋‹จ๊ณ„ BK21 ์ง€๋Šฅํ˜•๋ฐ˜๋„์ฒด ๊ต์œก์—ฐ๊ตฌ๋‹จ (์ฐธ์—ฌ)
  • IITP ์ •๋ณดํ†ต์‹ ๋ฐฉ์†กํ˜์‹ ์ธ์žฌ์–‘์„ฑ ๋ฉ”ํƒ€๋ฒ„์Šค์œตํ•ฉ๋Œ€ํ•™์› (์ฐธ์—ฌ)

Contact

Kunwoo Park / ๋ฐ• ๊ฑด์šฐ (kunwoo.park at ssu dot ac dot kr)

์—ฐ๊ตฌ ํ˜‘์—…, ์‚ฐํ•™ ํ˜‘๋ ฅ ๋“ฑ ๋‹ค์–‘ํ•œ ํ˜•ํƒœ์˜ ํ˜‘์—…์„ ํ™˜์˜ํ•ฉ๋‹ˆ๋‹ค.

News

Sep 30th, 2024

Prof. Park won the Outstanding Reviewer Award at EMNLP 2024.

Sep 30th, 2024

We placed runner-up at the AVeriTeC challenge, aiming to verify real-world claims using LLMs (collaboration with maum.ai and Adobe Research). Our system is invited as an oral presentation at the FEVER workshop co-located with EMNLP 2024.

May 16th, 2024

A joint work with Adobe Research has been accepted to ACL 2024.

Mar 8th, 2024

A paper is accepted for publication in IEEE Access. We introduced QuoteCSE++, a data-centric contrastive embedding framework for contextomy detection.

Feb 20th, 2024

A collaborative work with IU has been accepted to LREC-COLING 2024. We investigated how ChatGPT is aligned with human's views on explanation quality.

Dec 21th, 2023

A study on the LLM's ability of mathematical reasoning won the Outstanding Paper award at KSC 2023 (์ •๋ณด๊ณผํ•™ํšŒ ๋™๊ณ„ํ•™์ˆ ๋Œ€ํšŒ).

Oct 17th, 2023

A paper is accepted to EMNLP 2023 (Findings) based on collaboration with TUNiB. We introduce K-HATERS, the largest hate speech detection corpus in Korean.

July 17th, 2023

Our collaborative study with Adobe Research won the Hyundai Motors Best Paper Award at CKAIA (ํ•œ๊ตญ์ธ๊ณต์ง€๋Šฅํ•™ํšŒ).

July 6th, 2023

A joint work with UCLA is accepted for publication in EPJ Data Science (Title: Perceived Gender Cues from Social Media Photographs and its Relations to Electoral Success).

... see all News