Pith. sign in

REVIEW 7 cited by

A Length-Extrapolatable Transformer

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2212.10554 v1 pith:H42ESIK7 submitted 2022-12-20 cs.CL

Yutao Sun , Li Dong , Barun Patra , Shuming Ma , Shaohan Huang , Alon Benhaim , Vishrav Chaudhary , Xia Song
show 1 more author
Furu Wei
This is my paper · ORCID
classification cs.CL
keywords attentionextrapolationresolutionmodelingpositiontransformertransformersabove
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Position modeling plays a critical role in Transformers. In this paper, we focus on length extrapolation, i.e., training on short texts while evaluating longer sequences. We define attention resolution as an indicator of extrapolation. Then we propose two designs to improve the above metric of Transformers. Specifically, we introduce a relative position embedding to explicitly maximize attention resolution. Moreover, we use blockwise causal attention during inference for better resolution. We evaluate different Transformer variants with language modeling. Experimental results show that our model achieves strong performance in both interpolation and extrapolation settings. The code will be available at https://aka.ms/LeX-Transformer.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 7 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Robust Filter Attention: Self-Attention as Precision-Weighted State Estimation

    cs.LG 2025-09 unverdicted novelty 7.0 of 10

    Robust Filter Attention models self-attention as consistency-based state estimation under a linear SDE for token trajectories, matching standard attention complexity while showing lower perplexity and better zero-shot...

  2. AbsenceBench: Language Models Can't Tell What's Missing

    cs.CL 2025-06 conditional novelty 6.0 of 10

    LLMs that ace Needle-in-a-Haystack struggle to identify deliberately omitted content, a new benchmark called AbsenceBench shows.

  3. SAC-MIL: Spatial-Aware Correlated Multiple Instance Learning for Histopathology Whole Slide Image Classification

    cs.CV 2025-09 conditional novelty 5.0 of 10

    A spatial-aware MLP-Mixer with polar rotary position embedding and channel-shifting SAC blocks achieves state-of-the-art slide-level classification on CAMELYON-16, TCGA-LUNG, and TCGA-BRCA.

  4. Docopilot: Improving Multimodal Models for Document-Level Understanding

    cs.CV 2025-07 conditional novelty 5.0 of 10

    A new academic-paper dataset and a retrieval-free fine-tuned InternVL2 model improve multi-page document QA accuracy and latency on several benchmarks.

  5. MiniLongBench: The Low-cost Long Context Understanding Benchmark for Large Language Models

    cs.CL 2025-05 conditional novelty 5.0 of 10

    MiniLongBench, a 237-sample compression of LongBench, is claimed to reproduce model rankings with a 0.97 Spearman correlation at 4.5% of the evaluation cost.

  6. HoPE: Hyperbolic Rotary Positional Encoding for Stable Long-Range Dependency Modeling in Large Language Models

    cs.CL 2025-09 reject novelty 4.0 of 10

    HoPE replaces RoPE's sine/cosine rotations with hyperbolic functions plus an exponential damping term to enforce monotonic attention decay, but the claimed consistent superiority and the 'RoPE as special case' theorem...

  7. A Survey of Retentive Network

    cs.CL 2025-06 conditional novelty 2.0 of 10

    A review that describes the RetNet architecture and enumerates its applications across many domains, without presenting new experimental results.

Pith tools