Papers › Learning vs Retrieval: The Role of In-Context Examples in Regression with LLMs

Learning vs Retrieval: The Role of In-Context Examples in Regression with LLMs

6 Sep 2024arXiv:2409.04318archive 2025-07-28

Aliakbar Nafar, Kristen Brent Venable, Parisa Kordjamshidi

Generative Large Language Models (LLMs) are capable of being in-context learners. However, the underlying mechanism of in-context learning (ICL) is still a major research question, and experimental research results about how models exploit ICL are not always consistent. In this work, we propose a framework for evaluating in-context learning mechanisms, which we claim are a combination of retrieving internal knowledge and learning from in-context examples by focusing on regression tasks. First, we show that LLMs can perform regression on real-world datasets and then design experiments to measure the extent to which the LLM retrieves its internal knowledge versus learning from in-context examples. We argue that this process lies on a spectrum between these two extremes. We provide an in-depth analysis of the degrees to which these mechanisms are triggered depending on various factors, such as prior knowledge about the tasks and the type and richness of the information provided by the in-context examples. We employ three LLMs and utilize multiple datasets to corroborate the robustness of our findings. Our results shed light on how to engineer prompts to leverage meta-learning from in-context examples and foster knowledge retrieval depending on the problem being addressed.

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: 12 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 5 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 12 samples from 1 repository, 12 ran (10 with no instrument failure; 2 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.

HLR/LvsR-LLM officialSyntology: 12 samples, 12 ran (2 instrument-failed) · 0 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: 12 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 5 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 0 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.

5ran · honoured contract
2ran · our draft was wrong
5ran

Licence: 12 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 HLR/LvsR-LLM. “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.

HLR/LvsR-LLM official repository 12 samples, 12 ran (2 instrument-failed) · 0 unverified
create_IO_example utils.py ran no licence file found · pointer only · a7103037fea193cf · report fixture: signature dataset:str/0/str, x:list/1/float, y:float/0/float, feature_num:int/0/int, Names:list/1/str, config:str/0/str, is_test:bool/0/bool · returned tuple · level recorded 2026-09-24
create_file_name utils.py ran no licence file found · pointer only · 2d0a9726e7f08256 · report fixture: signature output_folder:str/0/str, dataset:str/0/str, model_name:str/0/str, in_context:int/0/int, feature_num:int/0/int, configs:str/0/str, testing_sampling:str/0/str · returned str · level recorded 2026-09-24
evaluate_model in 54 papers Datasets/model_training.py ran no licence file found · pointer only · ee73f674640a4661 · report fixture: signature name:str/0/str, y_true:ndarray/1/float, y_pred:ndarray/1/float, dataset:str/0/str, feature_number:int/0/int, sample_num:int/0/int, random_output:dict/0/? · returned dict · level recorded 2026-09-24
generate_random_chance_of_admission Datasets/utils.py ran · honoured contract fingerprinted no licence file found · pointer only · bd90d7e0a54821fe · report fixture: signature mean:float/0/float, std:float/0/float · returned float · level recorded 2026-09-24
generate_random_charges_usedcar Datasets/utils.py ran · honoured contract fingerprinted no licence file found · pointer only · 81ffacf0b35b7f76 · report fixture: signature mean:float/0/float, std:float/0/float · returned float · level recorded 2026-09-24
generate_random_output utils.py ran · honoured contract fingerprinted no licence file found · pointer only · 887a84fd93372282 · report fixture: signature dataset:str/0/str · returned float · level recorded 2026-09-24
generate_random_output Datasets/utils.py ran · honoured contract fingerprinted no licence file found · pointer only · 05223f06301a425a · report fixture: signature dataset:str/0/str · returned float · level recorded 2026-09-24
get_drop_list Datasets/model_training.py ran fingerprinted no licence file found · pointer only · f7a371212c0b807c · report fixture: signature dataset:str/0/str, feature_number:int/0/int, Y_label:str/0/str · returned list · level recorded 2026-09-24
preprocess_usedcars Datasets/data_preprocessing.py ran · honoured contract no licence file found · pointer only · 2b74fb1168aa2682 · report fixture: signature df:DataFrame/0/? · returned DataFrame · level recorded 2026-09-24
process_admission_chance reader.py ran · our draft was wrong no licence file found · pointer only · 3494677b1e2970bc · report fixture: signature df_incontext:DataFrame/0/?, df_test:DataFrame/0/? · returned tuple · level recorded 2026-09-24
process_insurance_cost reader.py ran · our draft was wrong no licence file found · pointer only · a49115e866e69018 · report fixture: signature df_incontext:DataFrame/0/?, df_test:DataFrame/0/? · returned tuple · level recorded 2026-09-24
read_dataset in 32 papers reader.py ran no licence file found · pointer only · 03675993a6b6403b · report fixture: signature dataset:str/0/str, config:str/0/str · returned tuple · level recorded 2026-09-24

Tasks

In-Context LearningMeta-LearningRetrievalregression

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