공대생 도전 일지

RemoteRAG: A Privacy-Preserving LLM Cloud RAG Service

https://aclanthology.org/2025.findings-acl.197/ RemoteRAG: A Privacy-Preserving LLM Cloud RAG ServiceYihang Cheng, Lan Zhang, Junyang Wang, Mu Yuan, Yunhao Yao. Findings of the Association for Computational Linguistics: ACL 2025. 2025.aclanthology.org Cloud RAG에서 사용자의 쿼리를 숨기면서 완전한 암호화 방식처럼 엄청난 계산 비용을 지불하지 않고 정확한 검색을 할 수 있는가 라는 문제를 해결하는 것이 핵심입니다. 기존 쿼리 임베딩을 클라우드에 보내는 것이 아닌 DP로 교란한 임베딩을 보내 후보 문서 집..

LargePiG: Your Large Language Model is Secretly a Pointer Generator

https://arxiv.org/abs/2410.11366 LargePiG: Your Large Language Model is Secretly a Pointer GeneratorRecent research on query generation has focused on using Large Language Models (LLMs), which despite bringing state-of-the-art performance, also introduce issues with hallucinations in the generated queries. In this work, we introduce relevance hallucinatiarxiv.org기존 LLM을 학습 없이 Pointer Generator처럼..

PositionID: LLMs can Control Lengths, Copy and Pastewith Explicit Positional Awareness

https://aclanthology.org/2024.findings-emnlp.983/ PositionID: LLMs can Control Lengths, Copy and Paste with Explicit Positional AwarenessNoah Wang, Feiyu Duan, Yibo Zhang, Wangchunshu Zhou, Ke Xu, Wenhao Huang, Jie Fu. Findings of the Association for Computational Linguistics: EMNLP 2024. 2024.aclanthology.org EMNLP 2024 findings네요 llm이 생성 중에 현재 위치를 명시적으로 추적하지 못하는 것을 positional awareness 부족으로 해석..

CopyNext: Explicit Span Copying and Alignment in Sequence to Sequence Mode

https://aclanthology.org/2020.spnlp-1.2/ CopyNext: Explicit Span Copying and Alignment in Sequence to Sequence ModelsAbhinav Singh, Patrick Xia, Guanghui Qin, Mahsa Yarmohammadi, Benjamin Van Durme. Proceedings of the Fourth Workshop on Structured Prediction for NLP. 2020.aclanthology.org이 논문도 조금 오래된 논문이네요 기존 copy mechanism의 한계를 해결하려고 합니다. 출력한 단어의 위치가 정확하게 표시되지 않고(입력에 동일한 단어가 있을 때 몇 번째 단어인지 알 수 ..

종이에 일단 작성하기 Table 1에 뭘 보여주면 설득이 될지 table 1 - 데이터 셋, Task를 2개 보여줘야 한다. https://huggingface.co/sentence-transformers sentence-transformers (Sentence Transformers)Running on T4huggingface.co임베딩 데이터 셋 https://huggingface.co/datasets/KorQuAD/squad_kor_v1 KorQuAD/squad_kor_v1 · Datasets at Hugging Face{ "text": [ "고뇌와 갈망 동기, 청춘의 사랑 동기" ], "answer_start": [ 115 ] }huggingface.co한글 Doc QA Data set..

https://aclanthology.org/P17-1099/ Get To The Point: Summarization with Pointer-Generator NetworksAbigail See, Peter J. Liu, Christopher D. Manning. Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2017.aclanthology.org2017 ACL 이네요 엄청 오래된 논문입니다. 2026.08.25 - [인공지능/논문 리뷰 or 진행] - Incorporating Copying Mechanism in Sequence-to-Sequenc..

https://aclanthology.org/P16-1154/ Incorporating Copying Mechanism in Sequence-to-Sequence LearningJiatao Gu, Zhengdong Lu, Hang Li, Victor O.K. Li. Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2016.aclanthology.org 2016년 ACL 논문입니다! 오래되긴 했네요2026.08.25 - [인공지능/논문 리뷰 or 진행] - Pointer Networks Pointer Networkshttps://arxiv.org/abs/..

https://arxiv.org/abs/1506.03134 Pointer NetworksWe introduce a new neural architecture to learn the conditional probability of an output sequence with elements that are discrete tokens corresponding to positions in an input sequence. Such problems cannot be trivially addressed by existent approaches sucarxiv.org 기존 Attention은 여러 hidden state를 가중합하여 정보를 가져왔다면 이 방법은 attention distribution 자체를 입력 ..

https://arxiv.org/abs/2602.08234 SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement LearningLarge Language Model (LLM) agents have shown stunning results in complex tasks, yet they often operate in isolation, failing to learn from past experiences. Existing memory-based methods primarily store raw trajectories, which are often redundant and noisearxiv.org에이전트가 과거의 긴 행동 궤적을 그대로 ..

https://aclanthology.org/2026.acl-long.69/ Reinforcement Learning for Self-Improving Agent with Skill LibraryJiongxiao Wang, Qiaojing Yan, Yawei Wang, Yijun Tian, Soumya Smruti Mishra, Zhichao Xu, Megha Gandhi, Panpan Xu, Lin Lee Cheong. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.aclanthology.org 이번 acl 2026 long으로 뽑힌 논문이..