Skip to main content

Natural Language Processing

Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs
·2075 words·10 mins· loading · loading
AI Generated ๐Ÿค— Daily Papers Natural Language Processing Large Language Models ๐Ÿข Tencent AI Lab
๋Œ€๊ทœ๋ชจ ์–ธ์–ด ๋ชจ๋ธ์˜ ๊ณผ๋„ํ•œ ์—ฐ์‚ฐ ๋ฌธ์ œ ํ•ด๊ฒฐ: ํšจ์œจ์ ์ธ ์ถ”๋ก ์„ ์œ„ํ•œ ์ƒˆ๋กœ์šด ์ง€ํ‘œ ๋ฐ ์ž๊ธฐ ํ•™์Šต ์ „๋žต ์ œ์‹œ
OneKE: A Dockerized Schema-Guided LLM Agent-based Knowledge Extraction System
·304 words·2 mins· loading · loading
AI Generated ๐Ÿค— Daily Papers Natural Language Processing Information Extraction ๐Ÿข Zhejiang University
OneKE: ๋„์ปค ๊ธฐ๋ฐ˜, ๋‹ค์ค‘ ์—์ด์ „ํŠธ LLM ์ง€์‹ ์ถ”์ถœ ์‹œ์Šคํ…œ์œผ๋กœ ์›น, PDF์—์„œ ๋‹ค์–‘ํ•œ ๋„๋ฉ”์ธ ์ง€์‹ ์ถ”์ถœ ๊ฐ€๋Šฅ
Xmodel-2 Technical Report
·2136 words·11 mins· loading · loading
AI Generated ๐Ÿค— Daily Papers Natural Language Processing Large Language Models ๐Ÿข Xiaoduo AI Lab
Xmodel-2: 12์–ต ๋งค๊ฐœ๋ณ€์ˆ˜์˜ ์ถ”๋ก  ์ „๋ฌธ ๋Œ€๊ทœ๋ชจ ์–ธ์–ด ๋ชจ๋ธ๋กœ, ํšจ์œจ์ ์ธ ์„ค๊ณ„์™€ ํ›ˆ๋ จ ์ „๋žต์„ ํ†ตํ•ด ์ตœ์ฒจ๋‹จ ์„ฑ๋Šฅ ๋‹ฌ์„ฑ!
Safeguard Fine-Tuned LLMs Through Pre- and Post-Tuning Model Merging
·177 words·1 min· loading · loading
AI Generated ๐Ÿค— Daily Papers Natural Language Processing Large Language Models ๐Ÿข Intel Labs
๋ฏธ์„ธ ์กฐ์ •์œผ๋กœ ์•ˆ์ „์„ฑ์ด ์ €ํ•˜๋œ LLM์˜ ์„ฑ๋Šฅ์„ ํ–ฅ์ƒ์‹œํ‚ค๋Š” ๋™์‹œ์— ์•ˆ์ „์„ฑ์„ ์œ ์ง€ํ•˜๋Š” ๊ฐ„ํŽธํ•˜๊ณ  ํšจ๊ณผ์ ์ธ ๋ชจ๋ธ ๊ฒฐํ•ฉ ๋ฐฉ๋ฒ• ์ œ์‹œ!
Token-Budget-Aware LLM Reasoning
·2417 words·12 mins· loading · loading
AI Generated ๐Ÿค— Daily Papers Natural Language Processing Large Language Models ๐Ÿข Nanjing University
ํ† ํฐ ์˜ˆ์‚ฐ ์ธ์‹ LLM ์ถ”๋ก  ํ”„๋ ˆ์ž„์›Œํฌ(TALE)๋ฅผ ํ†ตํ•ด LLM ์ถ”๋ก ์˜ ํ† ํฐ ๋น„์šฉ์„ ํฌ๊ฒŒ ์ค„์ด๋ฉด์„œ ์„ฑ๋Šฅ ์ €ํ•˜๋ฅผ ์ตœ์†Œํ™”ํ–ˆ์Šต๋‹ˆ๋‹ค!
How "Real" is Your Real-Time Simultaneous Speech-to-Text Translation System?
·1013 words·5 mins· loading · loading
AI Generated ๐Ÿค— Daily Papers Natural Language Processing Machine Translation ๐Ÿข Fondazione Bruno Kessler
์‹ค์‹œ๊ฐ„ ๋™์‹œ ํ†ต์—ญ ์‹œ์Šคํ…œ์˜ ํ˜„์‹ค์ ์ธ ํ•œ๊ณ„๋ฅผ ๊ทœ๋ช…ํ•˜๊ณ , ํ‘œ์ค€ํ™”๋œ ์šฉ์–ด์™€ ์ฒด๊ณ„๋ฅผ ์ œ์‹œํ•˜์—ฌ ์—ฐ๊ตฌ ๋ฐœ์ „์„ ์ด‰์ง„ํ•˜๋Š” ๋…ผ๋ฌธ.
CypherBench: Towards Precise Retrieval over Full-scale Modern Knowledge Graphs in the LLM Era
·2988 words·15 mins· loading · loading
AI Generated ๐Ÿค— Daily Papers Natural Language Processing Question Answering ๐Ÿข Megagon Labs
๋ณธ ์—ฐ๊ตฌ๋Š” ๋Œ€๊ทœ๋ชจ ํ˜„๋Œ€ ์ง€์‹ ๊ทธ๋ž˜ํ”„์—์„œ LLM์„ ์ด์šฉํ•œ ์ •ํ™•ํ•œ ์ •๋ณด ๊ฒ€์ƒ‰์„ ์œ„ํ•œ ์ƒˆ๋กœ์šด ๋ฒค์น˜๋งˆํฌ์ธ CypherBench๋ฅผ ์ œ์‹œํ•ฉ๋‹ˆ๋‹ค. ๊ธฐ์กด์˜ RDF ๊ธฐ๋ฐ˜ ์ง€์‹ ๊ทธ๋ž˜ํ”„๋Š” ๊ณผ๋„ํ•˜๊ฒŒ ํฐ ์Šคํ‚ค๋งˆ์™€ ๋ฆฌ์†Œ์Šค ์‹๋ณ„์ž ์‚ฌ์šฉ์œผ๋กœ LLM์— ๋น„ํšจ์œจ์ ์ด๋ผ๋Š” ๋ฌธ์ œ์ ์„ ๋ถ„์„ํ•ฉ๋‹ˆ๋‹ค. ํŠนํžˆ, Wikidata์™€ ๊ฐ™์€ ํ˜„๋Œ€ ์ง€์‹ ๊ทธ๋ž˜ํ”„๋Š” LLM์˜ ๋ฌธ๋งฅ ์ฐฝ ํฌ๊ธฐ๋ฅผ ์ดˆ๊ณผํ•˜๋Š” ๊ฒฝ์šฐ๊ฐ€ ๋งŽ์Šต๋‹ˆ…
YuLan-Mini: An Open Data-efficient Language Model
·3531 words·17 mins· loading · loading
AI Generated ๐Ÿค— Daily Papers Natural Language Processing Large Language Models ๐Ÿข Renmin University of China
YuLan-Mini: 24์–ต ๊ฐœ ๋งค๊ฐœ๋ณ€์ˆ˜๋ฅผ ๊ฐ€์ง„ ๋ฐ์ดํ„ฐ ํšจ์œจ์ ์ธ ๊ฐœ๋ฐฉํ˜• LLM
WavePulse: Real-time Content Analytics of Radio Livestreams
·2678 words·13 mins· loading · loading
AI Generated ๐Ÿค— Daily Papers Natural Language Processing Information Extraction ๐Ÿข New York University
WavePulse: ์‹ค์‹œ๊ฐ„ ๋ผ๋””์˜ค ๋ฐฉ์†ก ์ฝ˜ํ…์ธ  ๋ถ„์„ ํ”„๋ ˆ์ž„์›Œํฌ๊ฐ€ ์ •์น˜์  ๋‹ด๋ก , ๋ฏธ๋””์–ด ์œ ํ†ต, ์—ฌ๋ก  ๋™ํ–ฅ์„ ์‹ค์‹œ๊ฐ„ ๋ถ„์„ํ•˜์—ฌ ์ •์น˜ ๊ณผํ•™ ๋ฐ ๋ฏธ๋””์–ด ์—ฐ๊ตฌ์— ์ƒˆ๋กœ์šด ๊ฐ€๋Šฅ์„ฑ์„ ์—ด์—ˆ์Šต๋‹ˆ๋‹ค.
SBS Figures: Pre-training Figure QA from Stage-by-Stage Synthesized Images
·2234 words·11 mins· loading · loading
AI Generated ๐Ÿค— Daily Papers Natural Language Processing Question Answering ๐Ÿข Kyoto University
SBS Figures: 100๋งŒ ๊ฐœ์˜ ํ•ฉ์„ฑ ์ด๋ฏธ์ง€์™€ QA ์Œ์œผ๋กœ ์‚ฌ์ „ ํ•™์Šต๋œ, ํšจ์œจ์ ์ธ Figure QA ๋ชจ๋ธ!
ResearchTown: Simulator of Human Research Community
·16894 words·80 mins· loading · loading
AI Generated ๐Ÿค— Daily Papers Natural Language Processing Large Language Models ๐Ÿข University of Illinois Urbana-Champaign
RESEARCHTOWN: LLM ๊ธฐ๋ฐ˜ ์ธ๊ฐ„ ์—ฐ๊ตฌ ๊ณต๋™์ฒด ์‹œ๋ฎฌ๋ ˆ์ดํ„ฐ๋กœ, ๋‹ค์–‘ํ•œ ์—ฐ๊ตฌ ํ™œ๋™์„ ํ˜„์‹ค์ ์œผ๋กœ ๋ชจ๋ฐฉํ•˜๋ฉฐ ํ•™์ œ ๊ฐ„ ์—ฐ๊ตฌ ์•„์ด๋””์–ด ์ƒ์„ฑ ๊ฐ€๋Šฅ
In Case You Missed It: ARC 'Challenge' Is Not That Challenging
·2275 words·11 mins· loading · loading
AI Generated ๐Ÿค— Daily Papers Natural Language Processing Large Language Models ๐Ÿข Snowflake AI Research
๊ธฐ์กด ๋‹ค์ค‘ ์„ ํƒ ๋ฌธ์ œ ํ‰๊ฐ€ ๋ฐฉ์‹์˜ ์˜ค๋ฅ˜๋ฅผ ์ง€์ ํ•˜๊ณ , ๋ชจ๋“  ์˜ต์…˜์„ ํ•จ๊ป˜ ๊ณ ๋ คํ•˜๋Š” ์ƒˆ๋กœ์šด ํ‰๊ฐ€ ๋ฐฉ์‹์„ ์ œ์•ˆํ•˜์—ฌ ๋ชจ๋ธ ์„ฑ๋Šฅ ํ‰๊ฐ€์˜ ์ •ํ™•์„ฑ์„ ๋†’์˜€์Šต๋‹ˆ๋‹ค.
Friends-MMC: A Dataset for Multi-modal Multi-party Conversation Understanding
·1812 words·9 mins· loading · loading
AI Generated ๐Ÿค— Daily Papers Natural Language Processing Dialogue Systems ๐Ÿข Peking University
Friends-MMC: ๋ฐฉ๋Œ€ํ•œ ๋น„๋””์˜ค ๋ฐ์ดํ„ฐ์™€ ์ฃผ์„์„ ํฌํ•จํ•œ ์ƒˆ๋กœ์šด ๋‹ค์ค‘ ๋ชจ๋‹ฌ ๋‹ค์ค‘ ์ฐธ์—ฌ ๋Œ€ํ™” ๋ฐ์ดํ„ฐ์…‹์„ ํ†ตํ•ด ์‹ค์ œ ์„ธ๊ณ„์˜ ๋Œ€ํ™” ์ดํ•ด๋ฅผ ์œ„ํ•œ ์ƒˆ๋กœ์šด ๊ฐ€๋Šฅ์„ฑ์„ ์ œ์‹œํ•ฉ๋‹ˆ๋‹ค!
Fourier Position Embedding: Enhancing Attention's Periodic Extension for Length Generalization
·1717 words·9 mins· loading · loading
AI Generated ๐Ÿค— Daily Papers Natural Language Processing Large Language Models ๐Ÿข Tsinghua University
FoPE: ์ฃผํŒŒ์ˆ˜ ์˜์—ญ ํŠน์ง• ๊ฐœ์„ ์œผ๋กœ ๊ธด ๋ฌธ๋งฅ ๊ธธ์ด ์ผ๋ฐ˜ํ™” ๋‹ฌ์„ฑ!
DRT-o1: Optimized Deep Reasoning Translation via Long Chain-of-Thought
·366 words·2 mins· loading · loading
AI Generated ๐Ÿค— Daily Papers Natural Language Processing Machine Translation ๐Ÿข Tencent AI Lab
DRT-01 ๋ชจ๋ธ์€ ์žฅ๋ฌธ์˜ ์‚ฌ๊ณ  ๊ณผ์ •์„ ํ™œ์šฉํ•˜์—ฌ ๋ฌธํ•™ ๋ฒˆ์—ญ์˜ ์ •ํ™•๋„์™€ ์œ ์ฐฝ์„ฑ์„ ํฌ๊ฒŒ ํ–ฅ์ƒ์‹œ์ผฐ์Šต๋‹ˆ๋‹ค.
Diving into Self-Evolving Training for Multimodal Reasoning
·2584 words·13 mins· loading · loading
AI Generated ๐Ÿค— Daily Papers Natural Language Processing Large Language Models ๐Ÿข Hong Kong University of Science and Technology
M-STAR: ๋‹ค๋ชจ๋‹ฌ ์ถ”๋ก ์„ ์œ„ํ•œ ์ž๊ธฐ ์ง„ํ™” ํ›ˆ๋ จ์˜ ์ƒˆ๋กœ์šด ํ”„๋ ˆ์ž„์›Œํฌ๋ฅผ ์ œ์‹œ!
Deliberation in Latent Space via Differentiable Cache Augmentation
·2751 words·13 mins· loading · loading
AI Generated ๐Ÿค— Daily Papers Natural Language Processing Large Language Models ๐Ÿข Google DeepMind
๋Œ€๊ทœ๋ชจ ์–ธ์–ด ๋ชจ๋ธ์˜ ์ถ”๋ก  ์„ฑ๋Šฅ์„ ํ–ฅ์ƒ์‹œํ‚ค๋Š” ์ƒˆ๋กœ์šด ๋ฐฉ๋ฒ•์ธ โ€˜์ฐจ๋ณ„ ๊ฐ€๋Šฅํ•œ ์บ์‹œ ์ฆ๊ฐ•โ€™ ๊ธฐ๋ฒ• ์ œ์‹œ!
B-STaR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners
·1797 words·9 mins· loading · loading
AI Generated ๐Ÿค— Daily Papers Natural Language Processing Large Language Models ๐Ÿข Hong Kong University of Science and Technology
B-STAR: ์ž๊ธฐ ํ•™์Šต ์ถ”๋ก ์ž์—์„œ ํƒ์ƒ‰๊ณผ ํ™œ์šฉ์˜ ๊ท ํ˜•์„ ๋ชจ๋‹ˆํ„ฐ๋งํ•˜๊ณ  ์กฐ์ •ํ•˜์—ฌ ์„ฑ๋Šฅ์„ ํ–ฅ์ƒ์‹œํ‚ค๋Š” ์ƒˆ๋กœ์šด ํ”„๋ ˆ์ž„์›Œํฌ
Revisiting In-Context Learning with Long Context Language Models
·3818 words·18 mins· loading · loading
AI Generated ๐Ÿค— Daily Papers Natural Language Processing Large Language Models ๐Ÿข Google DeepMind
์žฅ๋ฌธ ์ปจํ…์ŠคํŠธ ์–ธ์–ด ๋ชจ๋ธ์—์„œ ์ •๊ตํ•œ ์ƒ˜ํ”Œ ์„ ํƒ ์ „๋žต๋ณด๋‹ค ๋ฌด์ž‘์œ„ ์ƒ˜ํ”Œ๋ง์ด ICL ์„ฑ๋Šฅ ํ–ฅ์ƒ์— ๋” ํšจ๊ณผ์ ์ด๋ฉฐ, ๋ฐ์ดํ„ฐ ์ฆ๊ฐ•์„ ํ†ตํ•ด ์ €์ž์› ์ž‘์—… ์„ฑ๋Šฅ์„ 5% ํ–ฅ์ƒ์‹œ์ผฐ๋‹ค๋Š” ๋†€๋ผ์šด ์—ฐ๊ตฌ ๊ฒฐ๊ณผ๋ฅผ ๋ฐœํ‘œ!
OpenRFT: Adapting Reasoning Foundation Model for Domain-specific Tasks with Reinforcement Fine-Tuning
·1880 words·9 mins· loading · loading
AI Generated ๐Ÿค— Daily Papers Natural Language Processing Large Language Models ๐Ÿข Beijing Jiaotong University
OpenRFT๋Š” ์ œํ•œ๋œ ๋„๋ฉ”์ธ ํŠน์ • ๋ฐ์ดํ„ฐ๋ฅผ ์‚ฌ์šฉํ•˜์—ฌ ์ผ๋ฐ˜์ ์ธ ์ถ”๋ก  ๋ชจ๋ธ์„ ๋ฏธ์„ธ ์กฐ์ •ํ•˜๋Š” ์ƒˆ๋กœ์šด ๋ฐฉ๋ฒ•์„ ์ œ์‹œํ•ฉ๋‹ˆ๋‹ค.