Papers › SEER : A Knapsack approach to Exemplar Selection for In-Context HybridQA

SEER : A Knapsack approach to Exemplar Selection for In-Context HybridQA

10 Oct 2023arXiv:2310.06675archive 2025-07-28

Jonathan Tonglet, Manon Reusens, Philipp Borchert, Bart Baesens

Question answering over hybrid contexts is a complex task, which requires the combination of information extracted from unstructured texts and structured tables in various ways. Recently, In-Context Learning demonstrated significant performance advances for reasoning tasks. In this paradigm, a large language model performs predictions based on a small set of supporting exemplars. The performance of In-Context Learning depends heavily on the selection procedure of the supporting exemplars, particularly in the case of HybridQA, where considering the diversity of reasoning chains and the large size of the hybrid contexts becomes crucial. In this work, we present Selection of ExEmplars for hybrid Reasoning (SEER), a novel method for selecting a set of exemplars that is both representative and diverse. The key novelty of SEER is that it formulates exemplar selection as a Knapsack Integer Linear Program. The Knapsack framework provides the flexibility to incorporate diversity constraints that prioritize exemplars with desirable attributes, and capacity constraints that ensure that the prompt size respects the provided capacity budgets. The effectiveness of SEER is demonstrated on FinQA and TAT-QA, two real-world benchmarks for HybridQA, where it outperforms previous exemplar selection methods.

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 16 code samples harvested from 1 repository linked to this paper: 6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 10 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 16 samples from 1 repository, 6 ran (5 with no instrument failure; 1 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 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.

jtonglet/seer officialmentioned in paperMITSyntology: 16 samples, 6 ran (1 instrument-failed) · 10 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

16 samples harvested: 6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 10 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.

2ran · honoured contract
1ran · our draft was wrong
3ran
10unverified

Licence: 0 of the 16 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 jtonglet/seer. “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.

jtonglet/seer official repository 16 samples, 6 ran (1 instrument-failed) · 10 unverified
eval_program evaluate_finqa.py ran · our draft was wrong fingerprinted MIT (permissive) · aee9ad37b0ad6acc · report fixture: signature program:list/1/str, table:list/1/list · returned tuple · level recorded 2026-09-22
get_candidates_fixed_set baselines.py ran MIT (permissive) · 51e425104cc5286c · report fixture: signature n_candidates:int/0/int, num_exemplars:int/0/int, dataset_size:int/0/int · returned list · level recorded 2026-09-24
get_random_set baselines.py ran MIT (permissive) · 4dfc9cdf96088786 · report fixture: signature instance_idx:int/0/int, valid_idx:ndarray/1/int, num_exemplars:int/0/int · returned list · level recorded 2026-09-24
gold_program_eval evaluation.py ran fingerprinted MIT (permissive) · 94fa99da8d852874 · report fixture: signature gold_program:str/0/str · returned str · level recorded 2026-09-24
process_row in 14 papers evaluate_finqa.py ran · honoured contract MIT (permissive) · 23577faa1c9d855a · report fixture: signature row_in:list/1/str · returned list · level recorded 2026-09-22
str_to_num evaluate_finqa.py ran · honoured contract fingerprinted MIT (permissive) · 6289f3a9b8166f42 · report fixture: signature text:str/0/str · returned float · level recorded 2026-09-22
create_hf_dataset_finqa finetune_bert.py unverified MIT (permissive) · 9245a4a89caa9029 · report
create_test_text_finqa finetune_bert.py unverified MIT (permissive) · cb8455b1e8c8bd7d · report
create_train_text_finqa finetune_bert.py unverified MIT (permissive) · 7384579da6eea90a · report
few_shot_chat_prompting codex_run.py unverified MIT (permissive) · 741a06e5d4794c85 · report
few_shot_prompting codex_run.py unverified MIT (permissive) · 8339cb160618ab6e · report
get_kate_set baselines.py unverified MIT (permissive) · 03f4b1c5c9cf651d · report
get_prompt_instance_finqa generate_prompt.py unverified MIT (permissive) · aca0b27eb683ac2c · report
get_prompt_instance_tatqa generate_prompt.py unverified MIT (permissive) · b7a03007a38c7ae3 · report
get_prompt_modality_finqa generate_prompt.py unverified MIT (permissive) · 340f562c1baaec58 · report
map_string evaluation.py unverified MIT (permissive) · e643b9c8cee2f454 · report

Tasks

DiversityIn-Context LearningLanguage ModelingLanguage ModellingLarge Language ModelQuestion Answering

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

1x1 ConvolutionAverage PoolingBatch NormalizationConvolutionCosine AnnealingDense ConnectionsGlobal Average PoolingGrouped ConvolutionLARSReLURegNetYSEERSigmoid ActivationSqueeze-and-Excitation BlockSwAV

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