공대생 도전 일지

https://academic.oup.com/cercor/article/33/8/4448/6702814 오 이 논문은 진짜 뇌에 대해 연구한 논문이었습니다. 사람이 언어를 어떻게 인지하여 뇌에서 판단하는지.... 이 연구는 Delta-band 신경 활동이 문장 처리에서 구문적 청크(chunking)와 의미적 연관성에 의해 어떻게 달라지는지를 비교MEG 데이터를 사용하여 1 Hz와 2 Hz 주파수 대역에서의 신경 반응을 측정하고, Word2Vec 모델로 예측한 의미적 연관성을 기반으로 신경 반응을 분석연구 결과, 구문적 청크 형성이 1 Hz 신경 반응을 주도하며, 의미적 연관성은 그 기여도가 상대적으로 낮음을 보여줌Sentence sequence와 paired-word sequence에서 강한 1 Hz 반..

https://arxiv.org/abs/2309.01918 RoboAgent: Generalization and Efficiency in Robot Manipulation via Semantic Augmentations and Action ChunkingThe grand aim of having a single robot that can manipulate arbitrary objects in diverse settings is at odds with the paucity of robotics datasets. Acquiring and growing such datasets is strenuous due to manual efforts, operational costs, and safety challen..

https://arxiv.org/abs/2410.13070 Is Semantic Chunking Worth the Computational Cost?Recent advances in Retrieval-Augmented Generation (RAG) systems have popularized semantic chunking, which aims to improve retrieval performance by dividing documents into semantically coherent segments. Despite its growing adoption, the actual benefits ovearxiv.org 제가 생각했던 내용을 논문으로 정리해놨는데성능이 나빠진 다는 것이 오히려 의외였습니다....

https://arxiv.org/abs/2404.12494 BIRD: A Trustworthy Bayesian Inference Framework for Large Language ModelsPredictive models often need to work with incomplete information in real-world tasks. Consequently, they must provide reliable probability or confidence estimation, especially in large-scale decision making and planning tasks. Current large language modelsarxiv.org    연구 목적대규모 언어 모델(LLM)의 확..

https://arxiv.org/abs/2307.05300 Unleashing the Emergent Cognitive Synergy in Large Language Models: A Task-Solving Agent through Multi-Persona Self-CollaboratioHuman intelligence thrives on cognitive synergy, where collaboration among different minds yield superior outcomes compared to isolated individuals. In this work, we propose Solo Performance Prompting (SPP), which transforms a single LLM..

https://arxiv.org/abs/2402.12327 Shall We Team Up: Exploring Spontaneous Cooperation of Competing LLM AgentsLarge Language Models (LLMs) have increasingly been utilized in social simulations, where they are often guided by carefully crafted instructions to stably exhibit human-like behaviors during simulations. Nevertheless, we doubt the necessity of shaping agearxiv.org 이 논문은 LLM 에이전트들이 경쟁적 환경에..

모델을 굽기 위해 데이터를 수집하면서 토큰 수 확인은 필수기에 한번 가지고 왔습니다.from datasets import list_datasets, load_dataset# 데이터셋 불러오기dataset = load_dataset("nvidia/ChatQA-Training-Data","synthetic_convqa")# 데이터셋 분할 정보 확인print(dataset)일단 데이터 불러오기!import pandas as pdimport tiktokendf = pd.DataFrame(dataset["train"])df이제 DataFrame으로 변경하고 데이터 형식 확인하기여기선 다른 이름이 많은데 저는 특정 column만 골라서 사용할 겁니다.import mathdef tokenize_in_batches(d..

https://arxiv.org/abs/2312.03720 Negotiating with LLMS: Prompt Hacks, Skill Gaps, and Reasoning DeficitsLarge language models LLMs like ChatGPT have reached the 100 Mio user barrier in record time and might increasingly enter all areas of our life leading to a diverse set of interactions between those Artificial Intelligence models and humans. While many stuarxiv.org 이 논문은 ChatGPT Turbo 3.5를 사용하..

https://arxiv.org/abs/2210.03629 ReAct: Synergizing Reasoning and Acting in Language ModelsWhile large language models (LLMs) have demonstrated impressive capabilities across tasks in language understanding and interactive decision making, their abilities for reasoning (e.g. chain-of-thought prompting) and acting (e.g. action plan generation) haarxiv.org Agent 관련 논문에서 빠질 수 없는 것이 ReAct기에...한 번 읽어..

https://arxiv.org/abs/2405.05248 LLMs with Personalities in Multi-issue Negotiation GamesPowered by large language models (LLMs), AI agents have become capable of many human tasks. Using the most canonical definitions of the Big Five personality, we measure the ability of LLMs to negotiate within a game-theoretical framework, as well as methodarxiv.org 이 논문은 LLM을 성격적 요소로 나눠서 협상을 진행하고, 그 결과를 보는 논..