SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2305.14788 · EMNLP · 2023

Adapting Language Models to Compress Contexts

Danqi Chen, Alexander Wettig, Alexis Chevalier, Anirudh Ajith

arXiv · PDF · Open in the Atlas

Code that ran

1 of 2 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 0 failures of our instrument; 1 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2305.14788.json · badge: /api/ran/2305.14788.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
princeton-nlp/AutoCompressors community
Papers with Code archive
1 ran · 1 no recorded run
FunctionStatusWhere it lives
CausalACOutputWithPast Ran
ran on a synthesized input · constructed an object; no result was computed
princeton-nlp/AutoCompressors/auto_compressor.py
pointer only (licence: NONE) · get_code("870363ebfde86294")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, princeton-nlp/AutoCompressors when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

AutoCompressorMixin Not yet run
unverified (harvested, no recorded run)
princeton-nlp/AutoCompressors/auto_compressor.py
pointer only (licence: NONE) · get_code("b4debd8fb9e1d482")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, princeton-nlp/AutoCompressors when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 distinct functions with an identity, 1 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 1 later) and 1 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
CausalACOutputWithPast
brick of this paper's assembly: helper
1 other paper
1 later
2404.07979 (2024-04)
LLoCO: Learning Long Contexts Offline

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Transformer-based language models (LMs) are powerful and widely-applicable tools, but their usefulness is constrained by a finite context window and the expensive computational cost of processing long text documents. We propose to adapt pre-trained LMs into AutoCompressors. These language models are capable of compressing long contexts into compact summary vectors, which are then accessible to the model as soft prompts. Summary vectors are trained with an unsupervised objective, whereby long documents are processed in segments, and summary vectors from all previous segments are used in language modeling. We fine-tune OPT and Llama-2 models on sequences of up to 30,720 tokens and show that AutoCompressors can utilize long contexts to improve perplexity. We evaluate AutoCompressors on in-context learning by compressing task demonstrations and find that summary vectors are good substitutes for plain-text demonstrations, increasing accuracy while reducing inference costs. Finally, we explore the benefits of pre-computing summary vectors for large corpora by applying summary vectors to retrievalaugmented language modeling and a passage re-ranking task. Overall, AutoCompressors emerge as a simple and inexpensive solution to extend the context window of LMs while speeding up inference over long contexts. 1 * AC and AW contributed equally. This work was done when AC was at the Institute for Advanced Study and visited the Princeton NLP group. 1 Our code and models are publicly available at https://github.com/princeton-nlp/AutoCompressors.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2305.14788")
get_code_for_paper("2305.14788")
have("2305.14788")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2305.14788.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2305.14788.svg)](https://syntology.ai/paper/2305.14788)

Connect an agent — have() is free.