Papers › Online Adaptation of Language Models with a Memory of Amortized Contexts

Online Adaptation of Language Models with a Memory of Amortized Contexts

7 Mar 2024arXiv:2403.04317archive 2025-07-28

Jihoon Tack, Jaehyung Kim, Eric Mitchell, Jinwoo Shin, Yee Whye Teh, Jonathan Richard Schwarz

Due to the rapid generation and dissemination of information, large language models (LLMs) quickly run out of date despite enormous development costs. To address the crucial need to keep models updated, online learning has emerged as a critical tool when utilizing LLMs for real-world applications. However, given the ever-expanding corpus of unseen documents and the large parameter space of modern LLMs, efficient adaptation is essential. To address these challenges, we propose Memory of Amortized Contexts (MAC), an efficient and effective online adaptation framework for LLMs with strong knowledge retention. We propose a feature extraction and memory-augmentation approach to compress and extract information from new documents into compact modulations stored in a memory bank. When answering questions, our model attends to and extracts relevant knowledge from this memory bank. To learn informative modulations in an efficient manner, we utilize amortization-based meta-learning, which substitutes an otherwise required optimization process with a single forward pass of the encoder. Subsequently, we learn to choose from and aggregate selected documents into a single modulation by conditioning on the question, allowing us to adapt a frozen language model during test time without requiring further gradient updates. Our experiment demonstrates the superiority of MAC in multiple aspects, including online adaptation performance, time, and memory efficiency. In addition, we show how MAC can be combined with and improve the performance of popular alternatives such as retrieval augmented generations (RAGs). Code is available at: https://github.com/jihoontack/MAC.

PaperPDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Syntology holds a reference implementation of Memory of Amortized Contexts (MAC), generated from the paper text (not the authors' code), at level 3 on Syntology's ladder: V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)”; V3 “paper-derived property tests pass on both of those same two generations.” (quoted from Syntology's server card). No rung compares this code against the authors' implementation. For agents: get_reference_implementation(name='Memory of Amortized Contexts (MAC)') (how to connect); the free check have('2403.04317') needs no token.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 15 code samples: 14 from 1 repository linked to this paper, 1 identical to code harvested from another paper's repository. Across all 15: 13 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 5 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 14 samples from 1 repository, 12 ran (7 with no instrument failure; 5 where Syntology's instrument failed); 1 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 4 of the 13 samples that ran have no recorded date.

jihoontack/mac officialmentioned in paperpytorchMITSyntology: 14 samples, 12 ran (5 instrument-failed) · 2 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

15 samples harvested: 13 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 5 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
5ran · violated contract
4ran · our draft was wrong
1ran; the contract check could not run
2ran
2unverified

Licence: 3 of the 15 samples are pointer only, meaning Syntology does not serve that copy's text. For 2 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from jihoontack/mac. 1 sample is listed last, in a group without a repository. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

jihoontack/mac official repository 14 samples, 12 ran (5 instrument-failed) · 2 unverified
clean_up utils.py ran · our draft was wrong fingerprinted MIT (permissive) · 28e11820c8f8d9f0 · report fixture: signature text:str/0/str · returned str · level recorded 2026-09-24
context_summarization evals/qa_utils.py ran MIT (permissive) · 4053ebe53b067c39 · report fixture: signature dataloader:list/1/dict, amort_model:callable/0/?, train:bool/0/bool · returned Tensor · level recorded 2026-09-24
decode_to_clean_text models/amortized_encdec.py ran · our draft was wrong MIT (permissive) · 4bc8c9e308a24e2f · report fixture: signature tokenizer:StandInTokenizer/0/?, ids:Tensor/2/int · returned list · level recorded 2026-09-22
default in 430 papers models/module/cross_attention.py ran · violated contract MIT (permissive) · 424012cb37b31172 · report fixture: signature val:NoneType/0/?, d:callable/0/? · returned int · level recorded 2026-09-22
embeddings_to_ids evals/qa_utils.py ran MIT (permissive) · 3e376007f812c566 · report fixture: signature embeddings:Tensor/2/float, embedding_matrix:Tensor/2/float, cos:bool/0/bool · returned Tensor · level recorded 2026-09-24
exact_match in 23 papers models/amortized_encdec.py ran · violated contract MIT (permissive) · 64702a446a4111bd · report fixture: signature prediction:str/0/str, ground_truth:str/0/str, match_length:bool/0/bool · returned bool · level recorded 2026-09-22
exists in 528 papers
census: 5 implementations from 103 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 1, kind int, dtype int64
models/module/cross_attention.py ran · violated contract MIT (permissive) here; the stored copy is pointer only · aa5486a3650902d8 · report fixture: signature val:Tensor/1/int · returned bool · level recorded, date not recorded
log_perplexity models/amortized_encdec.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) · 8f7b3874eb0e028a · report fixture: signature logits:Tensor/3/float, coeffs:Tensor/3/float · returned Tensor · level recorded, date not recorded
normalize_answer in 304 papers utils.py ran · our draft was wrong fingerprinted MIT (permissive) · c6a80c065d2e4851 · report fixture: signature s:str/0/str · returned str · level recorded 2026-09-22
pair in 101 papers models/module/self_attention.py ran · violated contract fingerprinted MIT (permissive) · 6ba8cee9f5daea41 · report fixture: signature t:int/0/int · returned tuple · level recorded, date not recorded
passprompt models/amortized_encdec.py ran · violated contract fingerprinted MIT (permissive) · 726980f025dbc7ee · report fixture: signature input1:Tensor/2/float, input2:Tensor/2/float, prompts:list/1/str · returned list · level recorded, date not recorded
uniq in 117 papers models/module/cross_attention.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 9a299fe5ae09e407 · report fixture: signature arr:list/1/int · returned dict_keys · level recorded 2026-09-22
AmortEncDecAggregateWrapper models/amortized_encdec.py unverified MIT (permissive) · 60f40382e49d0e3b · report
tqdm_distributed models/amortized_encdec.py unverified MIT (permissive) · e8baf90dada23a73 · report
Repository not located 1 sample, 1 ran (0 instrument-failed) · 0 unverified
1 sample is identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
f1_score in 121 papers repository not located ran · honoured contract fingerprinted licence of this copy not recorded · fdd9a4d20f5a9d6f · report fixture: signature prediction:str/0/str, ground_truth:str/0/str · returned float · level recorded 2026-09-22

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. For a generated assembly, an independent peer is a second implementation generated separately from the same paper text; neither implementation read the authors' code. At level 2 the two agreed numerically on the fixture's inputs; level 3 is recorded when property tests derived from the paper also passed on both, and each level 3 card prints how many its report lists. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. A generated assembly's label was set when its code was generated for the method, and no model judged it; its card prints it as "by construction" or "not judged by a model". Where an assembly's phrase has no constructed figure, a brick that ran is not among the harvested samples this build reads, and whether a brick's run only constructed an object is read from that brick's harvested sample, so the figure was not counted; it does not say there were none.

2 assemblies on this paper: 1 harvested, 1 generated.

generated Assembly for Memory of Amortized Contexts (MAC) (graph method: Memory of Amortized Contexts (MAC)), generated from the paper text, not the repository's code. 1 brick; individually on a fixture: 1 ran (1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. Ran end-to-end against an independent peer (level 3; 5 property tests passed on both).

label matches by construction: the code was generated for this method (not judged by a model)

  1. compute_cross_entropy_loss entry · level 3 · ran · honoured contract · 290b9bdb7c7098036f64aa373933db793b2ce084da381251a88727d84810bb64

harvested Assembly for Memory of Amortized Contexts (MAC) (graph method: Memory of Amortized Contexts (MAC)). 15 bricks; individually on a fixture: 13 ran (of which 7 constructed an object rather than computing a result; 11 with no instrument failure: 2 honoured, 2 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

  1. AmortEncDecAggregateWrapper entry · level 0 · unverified · 60f40382e49d0e3b
  2. Aggregator model · level 1 · ran · d7c5991fb3ad95d3
  3. MLP model · level 1 · ran · 774a535ca4637a4a
  4. PassPrompt model · level 1 · ran · 0b02000a67619d48
  5. TokenSelfAttend model · level 1 · ran · a771ed334b9182c6
  6. _get_batch_size helper · level 1 · ran · honoured contract · 184561e838f68d25
  7. decode_to_clean_text helper · level 1 · ran · our draft was wrong · 4bc8c9e308a24e2f
  8. exact_match helper · level 1 · ran · violated contract · 64702a446a4111bd
  9. f1_score helper · level 1 · ran · honoured contract · fdd9a4d20f5a9d6f
  10. tqdm_distributed helper · level 0 · unverified · e8baf90dada23a73
  11. CrossAttentionBlock model · level 1 · ran · f4251710501f26be
  12. FeedForward helper · level 1 · ran · 4eb35698130966be
  13. normalize_answer helper · level 1 · ran · our draft was wrong · c6a80c065d2e4851
  14. CrossAttention model · level 1 · ran · aa1cf692d15daa47
  15. exists helper · level 1 · ran · violated contract · aa5486a3650902d8

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2403.04317") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Language ModellingMeta-Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections