공대생 도전 일지

Chat QA1, Chat QA2

2024.12.23 - [인공지능/논문 리뷰 or 진행] - ChatQA: Surpassing GPT-4 on Conversational QA and RAG - 논문 리뷰 ChatQA: Surpassing GPT-4 on Conversational QA and RAG - 논문 리뷰https://arxiv.org/abs/2401.10225 ChatQA: Surpassing GPT-4 on Conversational QA and RAGIn this work, we introduce ChatQA, a suite of models that outperform GPT-4 on retrieval-augmented generation (RAG) and conversational question answering (Q..

ChatQA 2: Bridging the Gap to Proprietary LLMs in Long Context and RAG Capabilities - 논문 리뷰

https://arxiv.org/abs/2407.14482 ChatQA 2: Bridging the Gap to Proprietary LLMs in Long Context and RAG CapabilitiesIn this work, we introduce ChatQA 2, an Llama 3.0-based model with a 128K context window, designed to bridge the gap between open-source LLMs and leading proprietary models (e.g., GPT-4-Turbo) in long-context understanding and retrieval-augmented generatioarxiv.org RAG를 통해 GPT를 이겨보..

From Bias to Repair: Error as a Site of Collaboration and Negotiation in Applied Data Science Work - 논문 리뷰

https://dl.acm.org/doi/10.1145/3579607 From Bias to Repair: Error as a Site of Collaboration and Negotiation in Applied Data Science Work | Proceedings of the ACM on HManaging error has become an increasingly central and contested arena within data science work. While recent scholarship in artificial intelligence and machine learning has focused on limiting and eliminating error, practitioners h..

Negotiating becoming: a Nietzschean critique of large language models - 논문 리뷰

https://link.springer.com/article/10.1007/s10676-024-09783-5 이름에 Negotiating이 들어있어서 협상에 대한 내용이 나올 까 했는데 다른 내용이었습니다.ㅎㅎㅎ인간에 성장에 있어 LLM이 도움이 될까, 방해가 되지 않을까에 대해 니체의 철학적 개념을 통해 설명합니다.인간은 다양한 환경에서 불확실성이 주는 경험을 통해 성장하고, 조직을 이루어 나가는데 LLM은 학습한 데이터에서 가장 높은 확률을 출력하므로, 다양한 경험을 줄입니다. 이 것이 불확실성을 줄여버리고, 인간의 성장에 악조건을 만듭니다.이런 환경을 고치기 위해 llm을 좀 더 능동적으로, 투명하게 사용하자고 주장하네요   논문의 주제니체의 철학적 관점에서 대형 언어 모델(LLMs)이 인간의 자기..

https://aclanthology.org/2024.sigdial-1.63/ MindDial: Enhancing Conversational Agents with Theory-of-Mind for Common Ground Alignment and NegotiationShuwen Qiu, Mingdian Liu, Hengli Li, Song-Chun Zhu, Zilong Zheng. Proceedings of the 25th Annual Meeting of the Special Interest Group on Discourse and Dialogue. 2024.aclanthology.orghttps://arxiv.org/abs/2306.15253 MindDial: Belief Dynamics Trackin..

https://arxiv.org/abs/2401.10225 ChatQA: Surpassing GPT-4 on Conversational QA and RAGIn this work, we introduce ChatQA, a suite of models that outperform GPT-4 on retrieval-augmented generation (RAG) and conversational question answering (QA). To enhance generation, we propose a two-stage instruction tuning method that significantly boostsarxiv.org이 논문은 Opensource 모델로 GPT를 이겨보자! 하면서 나온 논문입니다.그래..

https://ieeexplore.ieee.org/document/10021626 Towards Emotion-Aware Agents for Improved User Satisfaction and Partner Perception in Negotiation DialoguesNegotiation is a complex social interaction that encapsulates emotional encounters in human decision-making. Virtual agents that can negotiate with humans by the means of language are useful in pedagogy and conversational AI. To advance the deve..

https://arxiv.org/abs/2402.11712 Modelling Political Coalition Negotiations Using LLM-based AgentsCoalition negotiations are a cornerstone of parliamentary democracies, characterised by complex interactions and strategic communications among political parties. Despite its significance, the modelling of these negotiations has remained unexplored with tharxiv.org 협상이긴 한데 뭔가 부족한 느낌입니다.그래도 결과를 높이려고 ..

https://arxiv.org/abs/2311.01876 Sentiment Analysis through LLM NegotiationsA standard paradigm for sentiment analysis is to rely on a singular LLM and makes the decision in a single round under the framework of in-context learning. This framework suffers the key disadvantage that the single-turn output generated by a single LLM marxiv.org 감정 분석의 정확도를 올리기 위해 협상? 토론? 을 사용했다는 논문입니다.제가 찾던 완전한 협상 논문..

https://arxiv.org/abs/2401.04536 Evaluating Language Model Agency through NegotiationsWe introduce an approach to evaluate language model (LM) agency using negotiation games. This approach better reflects real-world use cases and addresses some of the shortcomings of alternative LM benchmarks. Negotiation games enable us to study multi-turnarxiv.org 오 딱 제가 생각했던 Agent의 평가를 어떻게 해야 멀티턴에 적합하게, 벤치마크 ..