Papers › SetLexSem Challenge: Using Set Operations to Evaluate the Lexical and Semantic...

SetLexSem Challenge: Using Set Operations to Evaluate the Lexical and Semantic Robustness of Language Models

11 Nov 2024arXiv:2411.07336archive 2025-07-28

Bardiya Akhbari, Manish Gawali, Nicholas A. Dronen

Set theory is foundational to mathematics and, when sets are finite, to reasoning about the world. An intelligent system should perform set operations consistently, regardless of superficial variations in the operands. Initially designed for semantically-oriented NLP tasks, large language models (LLMs) are now being evaluated on algorithmic tasks. Because sets are comprised of arbitrary symbols (e.g. numbers, words), they provide an opportunity to test, systematically, the invariance of LLMs' algorithmic abilities under simple lexical or semantic variations. To this end, we present the SetLexSem Challenge, a synthetic benchmark that evaluates the performance of LLMs on set operations. SetLexSem assesses the robustness of LLMs' instruction-following abilities under various conditions, focusing on the set operations and the nature and construction of the set members. Evaluating seven LLMs with SetLexSem, we find that they exhibit poor robustness to variation in both operation and operands. We show -- via the framework's systematic sampling of set members along lexical and semantic dimensions -- that LLMs are not only not robust to variation along these dimensions but demonstrate unique failure modes in particular, easy-to-create semantic groupings of "deceptive" sets. We find that rigorously measuring language model robustness to variation in frequency and length is challenging and present an analysis that measures them independently. The code for reproducing the results of this paper, and for generating the SetLexSem Challenge dataset, is available at https://github.com/amazon-science/SetLexSem-Challenge.

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 23 code samples harvested from 1 repository linked to this paper: 19 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 0 violated, 4 with no contract checked; 13 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 13 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 23 samples from 1 repository, 19 ran (6 with no instrument failure; 13 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 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

amazon-science/setlexsem-challenge officialmentioned in paperApache-2.0Syntology: 23 samples, 19 ran (13 instrument-failed) · 4 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

23 samples harvested: 19 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 0 violated, 4 with no contract checked; 13 where Syntology's instrument failed) · 4 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.

2ran · honoured contract
13ran · our draft was wrong
4ran
4unverified

Licence: 0 of the 23 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 amazon-science/setlexsem-challenge. “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.

amazon-science/setlexsem-challenge official repository 23 samples, 19 ran (13 instrument-failed) · 4 unverified
agg setlexsem/analyze/hypothesis_testing_utils.py ran · honoured contract Apache-2.0 (permissive) · 50791cd8d19ae17c · report fixture: signature x:Series/1/float · returned Series · level recorded 2026-09-25
astype_set setlexsem/generate/generate_sets.py ran · our draft was wrong Apache-2.0 (permissive) · 6ee8c0ec3ee6a7a3 · report fixture: signature raw_input:str/0/str · returned set · level recorded 2026-09-22
create_single_plot setlexsem/analyze/visualize.py ran Apache-2.0 (permissive) · 382682b1f43803e2 · report fixture: signature data:DataFrame/0/?, hue_group:str/0/str, txt_title:str/0/str, legend_loc:str/0/str, plot_type:str/0/str, figure_size:tuple/1/int · returned Figure · level recorded 2026-09-25
create_subplots_1d setlexsem/analyze/visualize.py ran Apache-2.0 (permissive) · 01c3ce5d9fb476e6 · report fixture: signature data:DataFrame/0/?, hue_group:str/0/str, break_by:str/0/str, txt_title:str/0/str, legend_loc:str/0/str, plot_type:str/0/str · returned Figure · level recorded 2026-09-25
filter_dataframe setlexsem/analyze/error_analysis.py ran · our draft was wrong Apache-2.0 (permissive) · fea82b54e26300ae · report fixture: signature df_in:DataFrame/0/?, filter_criteria:dict/0/? · returned DataFrame · level recorded 2026-09-25
filter_words in 5 papers setlexsem/generate/sample.py ran · our draft was wrong Apache-2.0 (permissive) · 8431ddf5ad802651 · report fixture: signature words:list/1/str, item_len:int/0/int · returned list · level recorded 2026-09-25
generate_set_pair setlexsem/generate/generate_sets.py ran · our draft was wrong Apache-2.0 (permissive) · c653593d59f019e1 · report fixture: signature sampler:generator/0/? · returned tuple · level recorded 2026-09-22
get_normalized_count setlexsem/analyze/error_analysis.py ran · our draft was wrong Apache-2.0 (permissive) · 600bbee8e77f30f9 · report fixture: signature df_check:DataFrame/0/?, column_name:str/0/str · returned list · level recorded 2026-09-25
get_path_root setlexsem/constants.py ran · our draft was wrong Apache-2.0 (permissive) · 8d9b3e28920892c7 · report fixture: signature this_file:str/0/str · returned str · level recorded 2026-09-25
get_stats in 37 papers setlexsem/analyze/hypothesis_testing_utils.py ran · honoured contract Apache-2.0 (permissive) · 5afc0bf83778d553 · report fixture: signature df_in:DataFrame/0/? · returned DataFrame · level recorded 2026-09-25
make_english_list setlexsem/generate/prompt.py ran · our draft was wrong Apache-2.0 (permissive) · 642f476d5eddbdcf · report fixture: signature members:set/0/? · returned str · level recorded 2026-09-25
make_hps_prompt setlexsem/generate/generate_prompts.py ran Apache-2.0 (permissive) · f829eb3daa3cf327 · report fixture: signature op_list:list/1/str, k_shot:list/1/int, prompt_type:list/1/str, prompt_approach:list/1/str, is_fix_shot:list/1/bool, config:dict/0/? · returned generator · level recorded 2026-09-25
make_sampler_name_from_hps setlexsem/generate/sample.py ran · our draft was wrong Apache-2.0 (permissive) · ec9a1efddf07bd2e · report fixture: signature sampler_hps:dict/0/? · returned str · level recorded 2026-09-25
make_set setlexsem/generate/prompt.py ran · our draft was wrong Apache-2.0 (permissive) · b3f84cf0a92a6cb5 · report fixture: signature members:set/0/? · returned str · level recorded 2026-09-25
make_verb setlexsem/generate/prompt.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 3992b00cf71e89e3 · report fixture: signature members:list/1/str · returned str · level recorded 2026-09-25
parse_set_pair setlexsem/generate/generate_sets.py ran · our draft was wrong Apache-2.0 (permissive) · 39c5d1d50694781a · report fixture: signature raw_set_a:str/0/str, raw_set_b:str/0/str · returned tuple · level recorded 2026-09-22
read_yaml in 26 papers setlexsem/utils.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 493412c498a81a41 · report fixture: signature path_to_yaml:str/0/str · returned dict · level recorded 2026-09-25
replace_none setlexsem/generate/generate_prompts.py ran · our draft was wrong Apache-2.0 (permissive) · 7086c5b67a013729 · report fixture: signature list_in:list/1/str · returned list · level recorded 2026-09-25
viz_barplot setlexsem/analyze/visualize.py ran Apache-2.0 (permissive) · 7d0543bbfc5e3a17 · report fixture: signature df_res:DataFrame/0/?, hue_group:str/0/str, break_by:NoneType/0/?, filter_query:NoneType/0/?, save_fig:str/0/str, legend_loc:str/0/str, plot_type:str/0/str, figure_size:tuple/1/int · returned Figure · level recorded 2026-09-25
aws_auth setlexsem/experiment/lmapi.py unverified Apache-2.0 (permissive) · 7ec1a56a7fb2d0a6 · report
calculate_extra_info setlexsem/analyze/error_analysis.py unverified Apache-2.0 (permissive) · 7a11de2b701c8b62 · report
count_tokens in 39 papers setlexsem/experiment/lmapi.py unverified Apache-2.0 (permissive) · 912d808705da066a · report
invoke_bedrock setlexsem/experiment/lmapi.py unverified Apache-2.0 (permissive) · b063a2fc16acb1cd · report

Tasks

Instruction Following

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

SET

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