Papers
Topics
Authors
Recent
Search
2000 character limit reached

Periscope: Extending Frozen Language Models Beyond Their Context Window

Published 2 Oct 2026 in cs.CL, cs.IR, and cs.LG | (2610.04047v1)

Abstract: A LLM reads long text in one quadratic forward pass, stops at the context window, and loses accuracy with length before reaching it. We ask whether the read can be factorized when deciding over a finite set: which document is relevant, which option is supported, which passage is the evidence. Periscope, a training-free inference method, arranges the NN chunks of a text on a K×KK{\times}K grid with K=⌈N⌉K{=}\lceil\sqrt{N}\rceil and asks a frozen model the same question about KK local spans of consecutive chunks and KK strided spans that sample the whole text, reading the log-odds of every answer at one token. Each answer takes its best local and strided score, and scoring every chunk by its two spans gives an evidence map at no further cost, whose peak is the chunk behind the answer. Every probe is about sc\sqrt{sc} tokens for a text of ss tokens and chunk size cc, so a window of WW tokens reaches W2/cW^{2}/c tokens at s1.5s^{1.5} cost. The map replaces the long read. On LongBench v2, reading only the KK chunks the map ranks highest, 9k tokens, matches the same model's best window read across windows from 32k to 1M tokens, and on InfiniteBench, where the median context is 150k tokens, it leads the best window read by 5 points. The same map ranks BRIGHT's long-document corpora with the best NDCG@10 of six methods. Each call caches only one probe, so a 27B model reads 4.5M-token contexts on one 80GB GPU, where a single pass would need 296GB of cache. A long read then needs a GPU that holds the model, not one that holds the text.

Summary

No one has generated a summary of this paper yet.

Paper to Video (Beta)

No one has generated a video about this paper yet.

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Continue Learning

We haven't generated follow-up questions for this paper yet.

Tweets

Sign up for free to view the 2 tweets with 15 likes about this paper.