paper-with-me

Papers

No Mean Feat: Simple, Strong Baselines for Context Compression

2025-10-23 · Yair Feldman, Yoav Artzi arxiv

Context compression reduces Transformer inference costs by replacing lengthy inputs with shorter pre-computed representations. It carries significant benefits for retrieval-augmented generation (RAG) and has attracted growing research attention. However, progress remains difficult to measure due to inconsistent evaluations and baselines. We design a standard, easy-to-reproduce evaluation suite for context compression, BenchPress, along with simple, high-performance baselines for English reading comprehension. BenchPress supports benchmarking across model scales, datasets, compression ratios, and short ($<$1K tokens) to mid-range ($<$8K tokens) contexts. While the suite is applicable to any compression paradigm, our baselines target soft context compression. We establish two simple baselines that strongly outperform the widely used causal compression-token approach: mean pooling and a bidirectional compression-token variant. Our results show the benefit of bidirectional attention when computing compressed representations, and that simple pooling is an expressive compression operator.

📄 PDF Abstract BibTeX arXiv:2510.20797

Code (0)

등록된 구현이 없습니다.

Tasks

Reading Comprehension

Similar Papers 제목 키워드 기반

Simplification Using Paraphrases and Context-Based Lexical Substitution

2018-06-01 · NAACL 2018 6 · Reno Kriz, Eleni Miltsakaki, Marianna Apidianaki, Chris Callison-Burch

Lexical simplification involves identifying complex words or phrases that need to be simplified, and recommending simpler meaning-preserving substitutes that can be more easily understood. We propose a complex word ident…

Complex Word IdentificationLexical SimplificationText Simplification

Context-aware Neural Machine Translation with Mini-batch Embedding

2021-04-01 · EACL 2021 2 · Makoto Morishita, Jun Suzuki, Tomoharu Iwata, Masaaki Nagata

It is crucial to provide an inter-sentence context in Neural Machine Translation (NMT) models for higher-quality translation. With the aim of using a simple approach to incorporate inter-sentence information, we propose …

Machine TranslationNMTSentenceTranslation

Dual Graph Convolutional Network for Semantic Segmentation

2019-09-13 · Li Zhang, Xiangtai Li, Anurag Arnab, Kuiyuan Yang 외

Exploiting long-range contextual information is key for pixel-wise prediction tasks such as semantic segmentation. In contrast to previous work that uses multi-scale feature fusion or dilated convolutions, we propose a n…

Semantic Segmentation

Never a Dull Moment: Distributional Properties as a Baseline for Time-Series Classification

2023-03-31 · Trent Henderson, Annie G. Bryant, Ben D. Fulcher

The variety of complex algorithmic approaches for tackling time-series classification problems has grown considerably over the past decades, including the development of sophisticated but challenging-to-interpret deep-le…

ClassificationTime SeriesTime Series Classification

Context as Prior: Bayesian-Inspired Intent Inference for Non-Speaking Agents with a Household Cat Testbed

2026-04-30 · Wenqian Zhang, Zehao Wang arxiv

Many agents in real-world environments cannot reliably communicate their goals through language, including household pets, pre-verbal infants, and other non-speaking embodied agents. In such settings, intent must be infe…