Papers › Unveiling In-Context Learning: A Coordinate System to Understand Its Working Mechanism

Unveiling In-Context Learning: A Coordinate System to Understand Its Working Mechanism

24 Jul 2024arXiv:2407.17011archive 2025-07-28

Anhao Zhao, Fanghua Ye, Jinlan Fu, Xiaoyu Shen

Large language models (LLMs) exhibit remarkable in-context learning (ICL) capabilities. However, the underlying working mechanism of ICL remains poorly understood. Recent research presents two conflicting views on ICL: One emphasizes the impact of similar examples in the demonstrations, stressing the need for label correctness and more shots. The other attributes it to LLMs' inherent ability of task recognition, deeming label correctness and shot numbers of demonstrations as not crucial. In this work, we provide a Two-Dimensional Coordinate System that unifies both views into a systematic framework. The framework explains the behavior of ICL through two orthogonal variables: whether similar examples are presented in the demonstrations (perception) and whether LLMs can recognize the task (cognition). We propose the peak inverse rank metric to detect the task recognition ability of LLMs and study LLMs' reactions to different definitions of similarity. Based on these, we conduct extensive experiments to elucidate how ICL functions across each quadrant on multiple representative classification tasks. Finally, we extend our analyses to generation tasks, showing that our coordinate system can also be used to interpret ICL for generation tasks effectively.

PaperPDFCodeCode Syntology ran

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.

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

Code

Syntology 12 code samples harvested from 1 repository linked to this paper: 11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 12 samples from 1 repository, 11 ran (11 with no instrument failure; 0 where Syntology's instrument failed). 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 on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

eit-nlp/2d-coordinate-system-for-icl officialmentioned in papermentioned on GitHubpytorchMITSyntology: 12 samples, 11 ran (0 instrument-failed) · 1 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

12 samples harvested: 11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

11ran
1unverified

Licence: 0 of the 12 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from eit-nlp/2d-coordinate-system-for-icl. “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.

eit-nlp/2d-coordinate-system-for-icl official repository 12 samples, 11 ran (0 instrument-failed) · 1 unverified
first_quadrant_sst2 utils/first_quadrant_processing.py ran MIT (permissive) · a5f8c26c3b18acec · report fixture: signature wrapper:MockWrapper/0/?, train_dataset_list:list/1/dict, args:MockArgs/0/? · returned float · level recorded 2026-09-24
fourth_quadrant_emo utils/fourth_quadrant_processing.py ran MIT (permissive) · 6fb95e710c7c52a3 · report fixture: signature wrapper:MockWrapper/0/?, train_dataset_list:list/1/dict, args:Args/0/? · returned float · level recorded 2026-09-24
fourth_quadrant_trec utils/fourth_quadrant_processing.py ran MIT (permissive) · ea90a6dd70f35598 · report fixture: signature wrapper:MockWrapper/0/?, train_dataset_list:list/1/dict, args:Args/0/? · returned float · level recorded 2026-09-24
icl_generation utils/fourth_quadrant_processing.py ran MIT (permissive) · 87ae745630e3718d · report fixture: signature label_to_samples:dict/0/?, test_sample:str/0/str · returned str · level recorded 2026-09-24
icl_generation_color_and_capital utils/second_quadrant_processing.py ran MIT (permissive) · d5f6f01c6d67575d · report fixture: signature data:list/1/str, dissimilar_labels_indices:list/1/int, labels:list/1/str, random_data:str/0/str · returned str · level recorded 2026-09-24
icl_generation_sst2 utils/first_quadrant_processing.py ran MIT (permissive) · ffb2f4006315e711 · report fixture: signature label_to_samples:dict/0/?, test_sample:str/0/str · returned str · level recorded 2026-09-24
icl_generation_sst2 utils/second_quadrant_processing.py ran MIT (permissive) · 8dccec5f5228331d · report fixture: signature label_to_samples:dict/0/?, test_sample:str/0/str, args:Args/0/? · returned str · level recorded 2026-09-24
template_generation_color_and_capital utils/first_quadrant_processing.py ran fingerprinted MIT (permissive) · 6fa67476046b6014 · report fixture: signature data:list/1/str, labels:list/1/str · returned str · level recorded 2026-09-24
third_quadrant_emo utils/third_quadrant_processing.py ran MIT (permissive) · 13de22588444da78 · report fixture: signature wrapper:MockTokenizerWrapper/0/?, train_dataset_list:list/1/dict, args:MockArgs/0/? · returned list · level recorded 2026-09-24
third_quadrant_trec utils/third_quadrant_processing.py ran MIT (permissive) · 74d4b887b676e8e6 · report fixture: signature wrapper:MockWrapper/0/?, train_dataset_list:list/1/dict, args:MockArgs/0/? · returned list · level recorded 2026-09-24
tokenize in 176 papers task_recognition_pir.py ran MIT (permissive) · b9aa70482de54509 · report fixture: signature text:str/0/str, wrapper:MockWrapper/0/? · returned tuple · level recorded 2026-09-24
second_quadrant_sst2 utils/second_quadrant_processing.py unverified MIT (permissive) · 64e83651e7051164 · report

Tasks

In-Context 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