Kali Novskaya

🌸Подборка NeurIPS: LLM-статьи 🌸
#nlp #про_nlp #nlp_papers

Вот и прошёл NeurIPS 2024, самая большая конференция по машинному обучению. Ниже — небольшая подборка статей, которые мне показались наиболее интересными. Про некоторые точно стоит сделать отдельный обзор.

Агенты
🟣StreamBench: Towards Benchmarking Continuous Improvement of Language Agents arxiv  
🟣SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering arxiv  
🟣AgentBoard: An Analytical Evaluation Board of Multi-turn LLM Agents arxiv
 
🟣DiscoveryWorld: A Virtual Environment for Developing and Evaluating Automated Scientific Discovery Agents arxiv 

Бенчмарки
🟣DevBench: A multimodal developmental benchmark for language learning arxiv  
🟣CVQA: Culturally-diverse Multilingual Visual Question Answering Benchmark arxiv  
🟣LINGOLY: A Benchmark of Olympiad-Level Linguistic Reasoning Puzzles in Low-Resource and Extinct Languages arxiv  
🟣CLUE - Cross-Linked Unified Embedding for cross-modality representation learning arxiv  
🟣EmoBench: Evaluating the Emotional Intelligence of Large Language Models arxiv  

LLM
🟣The PRISM Alignment dataset: What Participatory, Representative and Individualised Human Feedback Reveals About the Subjective and Multicultural Alignment of Large Language Models arxiv  
🟣UniGen: A Unified Framework for Textual Dataset Generation via Large Language Models arxiv
🟣A Watermark for Black-Box Language Models arxiv

Please open Telegram to view this post

VIEW IN TELEGRAM

arXiv.org

StreamBench: Towards Benchmarking Continuous Improvement of Language Agents

Recent works have shown that large language model (LLM) agents are able to improve themselves from experience, which is an important ability for continuous enhancement post-deployment. However,...

www.group-telegram.com/br/rybolos_channel.com/1344

12.1K viewsDec 16 at 11:56

🌸Подборка NeurIPS: LLM-статьи 🌸
#nlp #про_nlp #nlp_papers

Вот и прошёл NeurIPS 2024, самая большая конференция по машинному обучению. Ниже — небольшая подборка статей, которые мне показались наиболее интересными. Про некоторые точно стоит сделать отдельный обзор.

Агенты
🟣StreamBench: Towards Benchmarking Continuous Improvement of Language Agents arxiv  
🟣SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering arxiv  
🟣AgentBoard: An Analytical Evaluation Board of Multi-turn LLM Agents arxiv
 
🟣DiscoveryWorld: A Virtual Environment for Developing and Evaluating Automated Scientific Discovery Agents arxiv 

Бенчмарки
🟣DevBench: A multimodal developmental benchmark for language learning arxiv  
🟣CVQA: Culturally-diverse Multilingual Visual Question Answering Benchmark arxiv  
🟣LINGOLY: A Benchmark of Olympiad-Level Linguistic Reasoning Puzzles in Low-Resource and Extinct Languages arxiv  
🟣CLUE - Cross-Linked Unified Embedding for cross-modality representation learning arxiv  
🟣EmoBench: Evaluating the Emotional Intelligence of Large Language Models arxiv  

LLM
🟣The PRISM Alignment dataset: What Participatory, Representative and Individualised Human Feedback Reveals About the Subjective and Multicultural Alignment of Large Language Models arxiv  
🟣UniGen: A Unified Framework for Textual Dataset Generation via Large Language Models arxiv
🟣A Watermark for Black-Box Language Models arxiv