paper-with-me

Papers

Self-Improving-Leaderboard(SIL): A Call for Real-World Centric Natural Language Processing Leaderboards

2023-03-20 · Chanjun Park, Hyeonseok Moon, Seolhwa Lee, Jaehyung Seo, Sugyeong Eo, Heuiseok Lim

Leaderboard systems allow researchers to objectively evaluate Natural Language Processing (NLP) models and are typically used to identify models that exhibit superior performance on a given task in a predetermined setting. However, we argue that evaluation on a given test dataset is just one of many performance indications of the model. In this paper, we claim leaderboard competitions should also aim to identify models that exhibit the best performance in a real-world setting. We highlight three issues with current leaderboard systems: (1) the use of a single, static test set, (2) discrepancy between testing and real-world application (3) the tendency for leaderboard-centric competition to be biased towards the test set. As a solution, we propose a new paradigm of leaderboard systems that addresses these issues of current leaderboard system. Through this study, we hope to induce a paradigm shift towards more real -world-centric leaderboard competitions.

📄 PDF Abstract BibTeX arXiv:2303.10888

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Test 설명 없음

Similar Papers 제목 키워드 기반

Narrowing the Coordinate-frame Gap in Behavior Prediction Models: Distillation for Efficient and Accurate Scene-centric Motion Forecasting

2022-06-08 · DiJia Su, Bertrand Douillard, Rami Al-Rfou, Cheolho Park 외

Behavior prediction models have proliferated in recent years, especially in the popular real-world robotics application of autonomous driving, where representing the distribution over possible futures of moving agents is…

Autonomous DrivingKnowledge DistillationMotion ForecastingMotion Planning+1

User-centric Subjective Leaderboard by Customizable Reward Modeling

2025-08-13 · Qi Jia, Xiujie Song, Zicheng Zhang, Yijin Guo 외 arxiv

Existing benchmarks for large language models (LLMs) predominantely focus on assessing their capabilities through verifiable tasks. Such objective and static benchmarks offer limited utility for practical LLM selection, …

HA-VLN: A Benchmark for Human-Aware Navigation in Discrete-Continuous Environments with Dynamic Multi-Human Interactions, Real-World Validation, and an Open Leaderboard

2025-03-18 · Yifei Dong, Fengyi Wu, Qi He, Heng Li 외

Vision-and-Language Navigation (VLN) systems often focus on either discrete (panoramic) or continuous (free-motion) paradigms alone, overlooking the complexities of human-populated, dynamic environments. We introduce a u…

BenchmarkingHuman DynamicsVision and Language Navigation

It's TIME: Towards the Next Generation of Time Series Forecasting Benchmarks

2026-02-12 · Zhongzheng Qiao, Sheng Pan, Anni Wang, Viktoriya Zhukova 외 arxiv

Time series foundation models (TSFMs) are revolutionizing the forecasting landscape from specific dataset modeling to generalizable task evaluation. However, we contend that existing benchmarks exhibit common limitations…

Time Series Forecasting

Memory Storyboard: Leveraging Temporal Segmentation for Streaming Self-Supervised Learning from Egocentric Videos

2025-01-21 · Yanlai Yang, Mengye Ren

Self-supervised learning holds the promise to learn good representations from real-world continuous uncurated data streams. However, most existing works in visual self-supervised learning focus on static images or artifi…

Continual LearningContrastive LearningEvent SegmentationSelf-Supervised Learning