Paper List

NLP & LLM & RAG & GenAI & Agent 에 대한 최신 논문 동향을 파악하고 리스트를 정리해보자!

Posting을 남기는 논문도 있고, 그렇지 않은 논문도 있습니다! 연도별 Paper List에 해당하는 각 논 하단에 원본 링크가 있다면 해당 논문은 읽은 것이고, 그렇지 않다면 읽을 예정인 논문입니다 😁

2025.

• HoarePrompt : Structural Reasoning About Program Correctness in Natural Language

• SWI : Speaking with Intent in Large Language Models

• 4bit-Quantization in Vector Embedding for RAG

• RAGVAL : Automatic Dataset Creation and Evaluation for RAG System

  • https://www.researchgate.net/publication/388465129_RAGVAL_Automatic_Dataset_Creation_and_Evaluation_for_RAG_Systems

• Qwen2.5 Technical Report

  • https://arxiv.org/pdf/2412.15115

• Balancing Content Size in RAG-Text2SQL System

  • https://arxiv.org/pdf/2502.15723v1

• Semantic Captioning : Benchmark Dataset and Graph-Aware Few-Shot In-Context Learning in SQL2Text

• SPSQL : Step-by-step Parsing Based Framework for Text-to-SQL Generation

• PET-SQL : A Prompt-Enhanced Two-round Refinement of Text-to-SQL with Cross-consistency

• Data Ambiguity Strikes Back: How Documentation Improves GPT's Text-to-SQL

  • https://arxiv.org/pdf/2310.18742

• Do We Need Domain-Specific Embedding Models? An Empirical Investigation

• Enhancig Text-to-SQL Translation for Financial System Design

  • https://arxiv.org/pdf/2312.14725

• Text2SQL is Not Enough : Unifying AI and Database with TAG

  • https://arxiv.org/pdf/2408.14717

• Don't Do RAG : When Cache-Augmented Generation is All you Need for Knowledge Tasks

  • https://arxiv.org/pdf/2412.15605

• BM25S : Ordered of magnitude fasteer lexical search via eagger sparse scoring

  • https://arxiv.org/pdf/2407.03618

• MEDEC : A Benchmark for Medical Error Detection and Correction in Clinical notes

  • https://arxiv.org/pdf/2412.19260

• Reciprocal Rank Fusion outperforms Condorcet and individual Rank Learning Methods

  • https://dl.acm.org/doi/10.1145/1571941.1572114

~ 2024.

• Retrieval Augmented Generation (RAG) and Beyond

  • https://arxiv.org/pdf/2409.14924v1

• ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT

  • https://arxiv.org/pdf/2004.12832

• Take a Step Back : Evoking Reasoning via Abstraction in Large Language Models

  • https://arxiv.org/pdf/2310.06117

• RAFT : Adapting Language Model to Domain Specific RAG

  • https://arxiv.org/pdf/2403.10131

• Interleaving Retrieval with Chain-of-Thought for Knowledge-Intensive Multi-Step Questions

  • https://arxiv.org/pdf/2212.10509

• RAG Survey : A Survey on Retrieval-Augmented Text Generation for Large Language Models

  • https://arxiv.org/pdf/2404.10981

• CoVe : Chain of Verification Reduces Hallucination in Large Language Models

  • https://arxiv.org/pdf/2309.11495

• Attention is all you need

  • https://arxiv.org/pdf/1706.03762