Skip to main content

Natural Language Processing

NILE: Internal Consistency Alignment in Large Language Models
·2709 words·13 mins· loading · loading
AI Generated ๐Ÿค— Daily Papers Natural Language Processing Large Language Models ๐Ÿข Chinese University of Hong Kong
NILE ํ”„๋ ˆ์ž„์›Œํฌ๋Š” LLM์˜ ๋‚ด๋ถ€ ์ง€์‹๊ณผ IFT ๋ฐ์ดํ„ฐ์…‹์˜ ์„ธ๊ณ„ ์ง€์‹ ๊ฐ„ ์ผ๊ด€์„ฑ์„ ๋†’์—ฌ LLM ์„ฑ๋Šฅ์„ ์ตœ๋Œ€ 68.5%๊นŒ์ง€ ํ–ฅ์ƒ์‹œํ‚ต๋‹ˆ๋‹ค.
Multi-LLM Text Summarization
·2623 words·13 mins· loading · loading
AI Generated ๐Ÿค— Daily Papers Natural Language Processing Text Summarization ๐Ÿข UC Santa Cruz
๋‹ค์ˆ˜์˜ ๊ฑฐ๋Œ€ ์–ธ์–ด ๋ชจ๋ธ(LLM)์„ ํ™œ์šฉํ•œ ํ˜์‹ ์ ์ธ ์žฅ๋ฌธ ์š”์•ฝ ํ”„๋ ˆ์ž„์›Œํฌ๊ฐ€ ์ œ์‹œ๋˜์–ด ์š”์•ฝ ํ’ˆ์งˆ์„ ์ตœ๋Œ€ 3๋ฐฐ ํ–ฅ์ƒ์‹œ์ผฐ์Šต๋‹ˆ๋‹ค!
Ensembling Large Language Models with Process Reward-Guided Tree Search for Better Complex Reasoning
·4085 words·20 mins· loading · loading
AI Generated ๐Ÿค— Daily Papers Natural Language Processing Large Language Models ๐Ÿข Microsoft Research
๋Œ€๊ทœ๋ชจ ์–ธ์–ด ๋ชจ๋ธ๋“ค์˜ ์•™์ƒ๋ธ”์„ ํ†ตํ•ด ๋ณต์žกํ•œ ์ถ”๋ก  ๋ฌธ์ œ๋ฅผ ๋”์šฑ ํšจ๊ณผ์ ์œผ๋กœ ํ•ด๊ฒฐํ•˜๋Š” ์ƒˆ๋กœ์šด ํ”„๋ ˆ์ž„์›Œํฌ, LE-MCTS๋ฅผ ์ œ์•ˆํ•ฉ๋‹ˆ๋‹ค!
TOMG-Bench: Evaluating LLMs on Text-based Open Molecule Generation
·3930 words·19 mins· loading · loading
AI Generated ๐Ÿค— Daily Papers Natural Language Processing Large Language Models ๐Ÿข Hong Kong Polytechnic University
TOMG-Bench: LLM ๊ธฐ๋ฐ˜ ์˜คํ”ˆ ๋ถ„์ž ์ƒ์„ฑ ๋ฒค์น˜๋งˆํฌ ์ œ์‹œ! 25๊ฐœ LLM ํ‰๊ฐ€ ๋ฐ ์ƒˆ๋กœ์šด instruction tuning ๋ฐ์ดํ„ฐ์…‹ OpenMolIns ๊ณต๊ฐœ๋กœ, ์˜คํ”ˆ์†Œ์Šค LLM์˜ ์„ฑ๋Šฅ ํ–ฅ์ƒ ๋ฐ ๋ถ„์ž ๋ฐœ๊ฒฌ์˜ ์ƒˆ๋กœ์šด ๊ฐ€๋Šฅ์„ฑ ์ œ์‹œ!
RobustFT: Robust Supervised Fine-tuning for Large Language Models under Noisy Response
·2295 words·11 mins· loading · loading
AI Generated ๐Ÿค— Daily Papers Natural Language Processing Large Language Models ๐Ÿข Peking University
ROBUSTFT๋Š” ์žก์Œ์ด ํฌํ•จ๋œ ์‘๋‹ต ์•„๋ž˜์—์„œ ๋Œ€๊ทœ๋ชจ ์–ธ์–ด ๋ชจ๋ธ์˜ ๊ฐ•๊ฑดํ•œ ์ง€๋„ ํ•™์Šต ๋ฏธ์„ธ ์กฐ์ •์„ ์œ„ํ•œ ํ”„๋ ˆ์ž„์›Œํฌ๋กœ, ์žก์Œ ๊ฐ์ง€ ๋ฐ ์žฌ๋ผ๋ฒจ๋ง์„ ํ†ตํ•ด ํ•˜๋ฅ˜ ์ž‘์—… ์„ฑ๋Šฅ์„ ํ–ฅ์ƒ์‹œํ‚ต๋‹ˆ๋‹ค.
ReMoE: Fully Differentiable Mixture-of-Experts with ReLU Routing
·4863 words·23 mins· loading · loading
AI Generated ๐Ÿค— Daily Papers Natural Language Processing Large Language Models ๐Ÿข Tsinghua University
ReLU ๋ผ์šฐํŒ…์„ ์‚ฌ์šฉํ•˜๋Š” ์™„์ „ ๋ฏธ๋ถ„ ๊ฐ€๋Šฅํ•œ MoE ์•„ํ‚คํ…์ฒ˜ ReMoE๋ฅผ ํ†ตํ•ด ๋Œ€๊ทœ๋ชจ ์–ธ์–ด ๋ชจ๋ธ์˜ ํ™•์žฅ์„ฑ๊ณผ ํšจ์œจ์„ฑ์„ ํš๊ธฐ์ ์œผ๋กœ ๊ฐœ์„ ํ–ˆ์Šต๋‹ˆ๋‹ค!
Outcome-Refining Process Supervision for Code Generation
·2498 words·12 mins· loading · loading
AI Generated ๐Ÿค— Daily Papers Natural Language Processing Large Language Models ๐Ÿข Peking University
๋ณต์žกํ•œ ์•Œ๊ณ ๋ฆฌ์ฆ˜ ์ถ”๋ก ์ด ํ•„์š”ํ•œ ์ฝ”๋“œ ์ƒ์„ฑ ๊ณผ์ œ์—์„œ ๊ธฐ์กด์˜ ํ•œ๊ณ„๋ฅผ ๊ทน๋ณตํ•˜๋Š” ์ƒˆ๋กœ์šด ๋ฐฉ๋ฒ•๋ก , Outcome-Refining Process Supervision (ORPS) ์ œ์‹œ
MixLLM: LLM Quantization with Global Mixed-precision between Output-features and Highly-efficient System Design
·2237 words·11 mins· loading · loading
AI Generated ๐Ÿค— Daily Papers Natural Language Processing Large Language Models ๐Ÿข Microsoft Research
MixLLM: ์ถœ๋ ฅ ํŠน์ง• ๊ฐ„์˜ ์ „์—ญ ํ˜ผํ•ฉ ์ •๋ฐ€๋„ ์–‘์žํ™”์™€ ๊ณ ํšจ์œจ ์‹œ์Šคํ…œ ์„ค๊ณ„๋ฅผ ํ†ตํ•ด LLM์˜ ์ •ํ™•๋„์™€ ํšจ์œจ์„ฑ์„ ๋™์‹œ์— ํ–ฅ์ƒ์‹œํ‚ค๋Š” ํš๊ธฐ์ ์ธ ์–‘์žํ™” ๋ฐฉ๋ฒ•
LLMs Lost in Translation: M-ALERT uncovers Cross-Linguistic Safety Gaps
·7524 words·36 mins· loading · loading
AI Generated ๐Ÿค— Daily Papers Natural Language Processing Large Language Models ๐Ÿข TU Darmstadt
M-ALERT๋Š” ๋‹ค๊ตญ์–ด LLM์˜ ์•ˆ์ „์„ฑ์„ ํ‰๊ฐ€ํ•˜๊ธฐ ์œ„ํ•œ ์ƒˆ๋กœ์šด ๋ฒค์น˜๋งˆํฌ์ž…๋‹ˆ๋‹ค. ์˜์–ด, ํ”„๋ž‘์Šค์–ด, ๋…์ผ์–ด, ์ดํƒˆ๋ฆฌ์•„์–ด, ์ŠคํŽ˜์ธ์–ด 5๊ฐœ ์–ธ์–ด์˜ 75,000๊ฐœ ํ”„๋กฌํ”„ํŠธ๋ฅผ ํฌํ•จํ•˜๋ฉฐ, ๋‹ค์–‘ํ•œ ์–ธ์–ด ๋ฐ ๋ฒ”์ฃผ์—์„œ LLM์˜ ์•ˆ์ „์„ฑ ๋ถˆ์ผ์น˜๋ฅผ ๋ฐํ˜€๋ƒˆ์Šต๋‹ˆ๋‹ค.
How to Synthesize Text Data without Model Collapse?
·5005 words·24 mins· loading · loading
AI Generated ๐Ÿค— Daily Papers Natural Language Processing Large Language Models ๐Ÿข Tsinghua University
ํ•ฉ์„ฑ ๋ฐ์ดํ„ฐ ๊ธฐ๋ฐ˜ ์–ธ์–ด ๋ชจ๋ธ ํ•™์Šต์˜ ๋ถ•๊ดด ๋ฌธ์ œ ํ•ด๊ฒฐ: ํ† ํฐ ํŽธ์ง‘ ๊ธฐ๋ฒ• ์ œ์‹œ!
Fietje: An open, efficient LLM for Dutch
·2556 words·12 mins· loading · loading
AI Generated ๐Ÿค— Daily Papers Natural Language Processing Large Language Models ๐Ÿข KU Leuven
Fietje: ์˜คํ”ˆ์†Œ์Šค ์†Œํ˜• ๋„ค๋œ๋ž€๋“œ์–ด LLM ๊ณต๊ฐœ!
AceMath: Advancing Frontier Math Reasoning with Post-Training and Reward Modeling
·2682 words·13 mins· loading · loading
AI Generated ๐Ÿค— Daily Papers Natural Language Processing Large Language Models ๐Ÿข NVIDIA Research
AceMath๋Š” ์‚ฌ์ „ ํ›ˆ๋ จ ๋ฐ ๋ณด์ƒ ๋ชจ๋ธ๋ง์„ ํ†ตํ•ด ์ตœ์ฒจ๋‹จ ์ˆ˜ํ•™ ์ถ”๋ก  ๋Šฅ๋ ฅ์„ ๋‹ฌ์„ฑํ•œ ํ”„๋Ÿฐํ‹ฐ์–ด๊ธ‰ ๋ชจ๋ธ ์‹œ๋ฆฌ์ฆˆ์ž…๋‹ˆ๋‹ค.
TheAgentCompany: Benchmarking LLM Agents on Consequential Real World Tasks
·2422 words·12 mins· loading · loading
AI Generated ๐Ÿค— Daily Papers Natural Language Processing Large Language Models ๐Ÿข Carnegie Mellon University
TheAgentCompany ๋ฒค์น˜๋งˆํฌ๋Š” ์‹ค์ œ ์†Œํ”„ํŠธ์›จ์–ด ํšŒ์‚ฌ ํ™˜๊ฒฝ์„ ๋ชจ๋ฐฉํ•˜์—ฌ LLM ์—์ด์ „ํŠธ์˜ ์‹ค์ œ ์—…๋ฌด ์ˆ˜ํ–‰ ๋Šฅ๋ ฅ์„ ํ‰๊ฐ€ํ•˜๋ฉฐ, AI ์—์ด์ „ํŠธ์˜ ํ˜„์‹ค ์„ธ๊ณ„ ์ ์šฉ ๊ฐ€๋Šฅ์„ฑ๊ณผ ํ•œ๊ณ„๋ฅผ ๋ณด์—ฌ์ค๋‹ˆ๋‹ค.
Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference
·2449 words·12 mins· loading · loading
AI Generated ๐Ÿค— Daily Papers Natural Language Processing Large Language Models ๐Ÿข Answer.AI
ModernBERT: ๋น ๋ฅด๊ณ  ๋ฉ”๋ชจ๋ฆฌ ํšจ์œจ์ ์ธ ์žฅ๋ฌธ ์ปจํ…์ŠคํŠธ ๋ฏธ์„ธ ์กฐ์ • ๋ฐ ์ถ”๋ก ์„ ์œ„ํ•œ ์ตœ์ฒจ๋‹จ ์–‘๋ฐฉํ–ฅ ์ธ์ฝ”๋”!
RAG-RewardBench: Benchmarking Reward Models in Retrieval Augmented Generation for Preference Alignment
·2978 words·14 mins· loading · loading
AI Generated ๐Ÿค— Daily Papers Natural Language Processing Large Language Models ๐Ÿข University of Chinese Academy of Sciences
RAG-RewardBench: RAG ํ™˜๊ฒฝ์—์„œ ๋ณด์ƒ ๋ชจ๋ธ ํ‰๊ฐ€๋ฅผ ์œ„ํ•œ ์ตœ์ดˆ์˜ ๋ฒค์น˜๋งˆํฌ ์ œ์‹œ!
AntiLeak-Bench: Preventing Data Contamination by Automatically Constructing Benchmarks with Updated Real-World Knowledge
·3149 words·15 mins· loading · loading
AI Generated ๐Ÿค— Daily Papers Natural Language Processing Large Language Models ๐Ÿข Nanyang Technological University
AntiLeak-Bench: ์ž๋™ํ™”๋œ ๋ฒค์น˜๋งˆํ‚น์œผ๋กœ LLM ๋ฐ์ดํ„ฐ ์˜ค์—ผ ๋ฐฉ์ง€
DateLogicQA: Benchmarking Temporal Biases in Large Language Models
·2927 words·14 mins· loading · loading
AI Generated ๐Ÿค— Daily Papers Natural Language Processing Large Language Models ๐Ÿข University of Aberdeen
DateLogicQA: LLM์˜ ์‹œ๊ฐ„์  ์ถ”๋ก  ํŽธํ–ฅ ๋ฒค์น˜๋งˆํฌ ์ œ์‹œ! ํ† ํฐํ™”, ํ‘œ์ƒ ๋ฐ ๋…ผ๋ฆฌ ์ˆ˜์ค€ ํŽธํ–ฅ ๋ถ„์„์œผ๋กœ ์‹œ๊ฐ„์  ๋ฐ์ดํ„ฐ ์ฒ˜๋ฆฌ ๊ฐœ์„  ๋ฐฉ์•ˆ ์ œ์‹œ!
Whisper-GPT: A Hybrid Representation Audio Large Language Model
·1322 words·7 mins· loading · loading
AI Generated ๐Ÿค— Daily Papers Natural Language Processing Large Language Models ๐Ÿข Stanford University
Whisper-GPT: ํ•˜์ด๋ธŒ๋ฆฌ๋“œ ์Œ์„ฑ ๋ฐ ์Œ์•… LLM์œผ๋กœ, ์—ฐ์† ์˜ค๋””์˜ค์™€ ์ด์‚ฐ ํ† ํฐ์„ ๊ฒฐํ•ฉํ•˜์—ฌ ํ–ฅ์ƒ๋œ ์„ฑ๋Šฅ์„ ์ œ๊ณตํ•ฉ๋‹ˆ๋‹ค.
The Open Source Advantage in Large Language Models (LLMs)
·248 words·2 mins· loading · loading
AI Generated ๐Ÿค— Daily Papers Natural Language Processing Large Language Models ๐Ÿข Rollins College
์˜คํ”ˆ์†Œ์Šค LLM, ํ์‡„ํ˜• LLM ๋Œ€๋น„ ํˆฌ๋ช…์„ฑ๊ณผ ์ ‘๊ทผ์„ฑ์€ ๋†’์ง€๋งŒ, ์„ฑ๋Šฅ์€ ๋‚ฎ์Œ. ํ•˜์ด๋ธŒ๋ฆฌ๋“œ ์ „๋žต์ด ๋ฏธ๋ž˜.
SPaR: Self-Play with Tree-Search Refinement to Improve Instruction-Following in Large Language Models
·3260 words·16 mins· loading · loading
AI Generated ๐Ÿค— Daily Papers Natural Language Processing Large Language Models ๐Ÿข Tsinghua University
Self-play with refinement boosts instruction-following in LLMs.