공대생 도전 일지

https://arxiv.org/abs/2405.19333 Multi-Modal Generative Embedding ModelMost multi-modal tasks can be formulated into problems of either generation or embedding. Existing models usually tackle these two types of problems by decoupling language modules into a text decoder for generation, and a text encoder for embedding. To exparxiv.org이 논문은 Multi-Modal이기도 하고, 이미지는 일단 나중에 생각할 거기 때문에 적당히 보고 넘어가겠습니다..

https://aclanthology.org/2025.coling-main.94/ Embedding-Informed Adaptive Retrieval-Augmented Generation of Large Language ModelsChengkai Huang, Yu Xia, Rui Wang, Kaige Xie, Tong Yu, Julian McAuley, Lina Yao. Proceedings of the 31st International Conference on Computational Linguistics. 2025.aclanthology.org그런데 이 논문은 Embedding + Gen은 아닌 잘 못 찾은 논문이라 ㅎㅎ... 그래도 재밌어서 쭉 읽어 봤습니다. 이 논문은 검색을 언제 진행할까가 주요..

https://aclanthology.org/2025.coling-main.549/ GEAR: A Simple GENERATE, EMBED, AVERAGE AND RANK Approach for Unsupervised Reverse DictionaryFatemah Yousef Almeman, Luis Espinosa Anke. Proceedings of the 31st International Conference on Computational Linguistics. 2025.aclanthology.org저는 RD라는 Task 자체를 처음 봤습니다.그래서 뭔가 했더니 설명을 주면 반대로 단어를 맞추는 것이네요신서유기가 생각나는 Task...제가 크게 관심있는 분야는 아니라 이런게 있다 정도만 보고 넘어갔습..

https://arxiv.org/abs/2010.03768 ALFWorld: Aligning Text and Embodied Environments for Interactive LearningGiven a simple request like Put a washed apple in the kitchen fridge, humans can reason in purely abstract terms by imagining action sequences and scoring their likelihood of success, prototypicality, and efficiency, all without moving a muscle. Once we searxiv.org     사람은 단순한 요청이 주어지면 Acti..

https://arxiv.org/abs/2206.10498 PlanBench: An Extensible Benchmark for Evaluating Large Language Models on Planning and Reasoning about ChangeGenerating plans of action, and reasoning about change have long been considered a core competence of intelligent agents. It is thus no surprise that evaluating the planning and reasoning capabilities of large language models (LLMs) has become a hot topic..

https://2024.aclweb.org/program/main_conference_papers/ Accepted Main Conference PapersACL 2024 Accepted Main Conference Papers2024.aclweb.orgACL논문은 여기서 확인 가능합니다.https://aclanthology.org/2024.acl-long.382/ Mirror: Multiple-perspective Self-Reflection Method for Knowledge-rich ReasoningHanqi Yan, Qinglin Zhu, Xinyu Wang, Lin Gui, Yulan He. Proceedings of the 62nd Annual Meeting of the Association..

https://arxiv.org/abs/2303.17651 Self-Refine: Iterative Refinement with Self-FeedbackLike humans, large language models (LLMs) do not always generate the best output on their first try. Motivated by how humans refine their written text, we introduce Self-Refine, an approach for improving initial outputs from LLMs through iterative feedbackarxiv.org 아이디어는 굉장히 단순하다. LLM을 통해 생산된 글을 다시 동일한 LLM에 넣어 피..

https://arxiv.org/abs/2405.06682 Self-Reflection in LLM Agents: Effects on Problem-Solving PerformanceIn this study, we investigated the effects of self-reflection in large language models (LLMs) on problem-solving performance. We instructed nine popular LLMs to answer a series of multiple-choice questions to provide a performance baseline. For each incorrarxiv.org CoT는 LLM의 성능을 크게 올리지만 논리, 수학적,..

https://aclanthology.org/2025.coling-main.504/ DORA: Dynamic Optimization Prompt for Continuous Reflection of LLM-based AgentKun Li, Tingzhang Zhao, Wei Zhou, Songlin Hu. Proceedings of the 31st International Conference on Computational Linguistics. 2025.aclanthology.org 기존 Reflcetion은 성능을 올리긴 했지만 iteration이 증가할 수록 성능 향상이 더뎌졌다.위 그래프에서 보듯 Early Stop Reflection문제가 발생하였고, DORA(Dynamic and Optimized..

https://arxiv.org/abs/2310.06271 Towards Mitigating Hallucination in Large Language Models via Self-ReflectionLarge language models (LLMs) have shown promise for generative and knowledge-intensive tasks including question-answering (QA) tasks. However, the practical deployment still faces challenges, notably the issue of "hallucination", where models generate plauarxiv.org 그럴듯하게 들리지만 사실이 아니거나 터무..