paper-with-me

홈 › Papers

The Needle in the haystack: Out-distribution aware Self-training in an Open-World Setting

2021-09-29 · Maximilian Augustin, Matthias Hein

Traditional semi-supervised learning (SSL) has focused on the closed world assumption where all unlabeled samples are task-related. In practice, this assumption is often violated when leveraging data from very large image databases that contain mostly non-task-relevant samples. While standard self-training and other established methods fail in this open-world setting, we demonstrate that our out-distribution-aware self-learning (ODST) with a careful sample selection strategy can leverage unlabeled datasets with millions of samples, more than 1600 times larger than the labeled datasets, and which contain only about $2\%$ task-relevant inputs. Standard and open world SSL techniques degrade in performance when the ratio of task-relevant sample decreases and show a significant distribution shift which is problematic regarding AI safety while ODST outperforms them with respect to test performance, corruption robustness and out-of-distribution detection.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Out-of-Distribution DetectionSelf-Learning

Methods 이 논문이 사용한 방법론

Test 설명 없음
Self-Learning 설명 없음

Similar Papers 제목 키워드 기반

SR-TTT: Surprisal-Aware Residual Test-Time Training

2026-02-26 · Swamynathan V P arxiv

Test-Time Training (TTT) language models achieve theoretically infinite context windows with an O(1) memory footprint by replacing the standard exact-attention KV-cache with hidden state ``fast weights'' W_fast updated v…

Self-Supervised Learning

Multimodal Needle in a Haystack: Benchmarking Long-Context Capability of Multimodal Large Language Models

2024-06-17 · Hengyi Wang, Haizhou Shi, Shiwei Tan, Weiyi Qin 외

Multimodal Large Language Models (MLLMs) have shown significant promise in various applications, leading to broad interest from researchers and practitioners alike. However, a comprehensive evaluation of their long-conte…

BenchmarkingHallucinationImage Retrieval+4

NoLiMa: Long-Context Evaluation Beyond Literal Matching

2025-02-07 · Ali Modarressi, Hanieh Deilamsalehy, Franck Dernoncourt, Trung Bui 외

Recent large language models (LLMs) support long contexts ranging from 128K to 1M tokens. A popular method for evaluating these capabilities is the needle-in-a-haystack (NIAH) test, which involves retrieving a "needle" (…

GOLD PANNING: Strategic Context Shuffling for Needle-in-Haystack Reasoning

2025-10-10 · Adam Byerly, Daniel Khashabi arxiv

Large language models (LLMs) exhibit pronounced position bias in long-context needle-in-haystack problems, systematically prioritizing the location of information over its relevance. While current mitigations rely on whi…

Active Learning

Fast Bayesian Optimization of Needle-in-a-Haystack Problems using Zooming Memory-Based Initialization (ZoMBI)

2022-08-26 · Alexander E. Siemenn, Zekun Ren, Qianxiao Li, Tonio Buonassisi

Needle-in-a-Haystack problems exist across a wide range of applications including rare disease prediction, ecological resource management, fraud detection, and material property optimization. A Needle-in-a-Haystack probl…

Bayesian OptimizationDisease PredictionFraud DetectionManagement