Papers › LADDER: Language Driven Slice Discovery and Error Rectification

LADDER: Language Driven Slice Discovery and Error Rectification

31 Jul 2024arXiv:2408.07832archive 2025-07-28

Shantanu Ghosh, Rayan Syed, Chenyu Wang, Clare B. Poynton, Shyam Visweswaran, Kayhan Batmanghelich

Error slice discovery is crucial to diagnose and mitigate model errors. Current clustering or discrete attribute-based slice discovery methods face key limitations: 1) clustering results in incoherent slices, while assigning discrete attributes to slices leads to incomplete coverage of error patterns due to missing or insufficient attributes; 2) these methods lack complex reasoning, preventing them from fully explaining model biases; 3) they fail to integrate domain knowledge, limiting their usage in specialized fields e.g. radiology. We propose\ladder (Language-Driven Discovery and Error Rectification), to address the limitations by: (1) leveraging the flexibility of natural language to address incompleteness, (2) employing LLM's latent domain knowledge and advanced reasoning to analyze sentences and derive testable hypotheses directly, identifying biased attributes, and form coherent error slices without clustering. Existing mitigation methods typically address only the worst-performing group, often amplifying errors in other subgroups. In contrast,\ladder generates pseudo attributes from the discovered hypotheses to mitigate errors across all biases without explicit attribute annotations or prior knowledge of bias. Rigorous evaluations on 6 datasets spanning natural and medical images -- comparing 200+ classifiers with diverse architectures, pretraining strategies, and LLMs -- show that\ladder consistently outperforms existing baselines in discovering and mitigating biases.

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 17 code samples harvested from 1 repository linked to this paper: 15 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 7 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 6 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: community (archive-listed): 17 samples from 1 repository, 15 ran (8 with no instrument failure; 7 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.

batmanlab/Ladder mentioned on GitHubpytorchCC-BY-4.0Syntology: 17 samples, 15 ran (7 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

17 samples harvested: 15 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 7 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.

6ran · our draft was wrong
1ran; the contract check could not run
8ran
2unverified

Licence: 17 of the 17 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 batmanlab/Ladder. “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.

batmanlab/Ladder community (archive-listed) 17 samples, 15 ran (7 instrument-failed) · 2 unverified
compute_AUC src/codebase/metrics.py ran · our draft was wrong CC-BY-4.0 · pointer only · 688ce138721d837e · report fixture: signature gt:Tensor/2/float, pred:Tensor/2/float · returned tuple · level recorded 2026-09-24
compute_accuracy in 81 papers src/codebase/metrics.py ran fingerprinted CC-BY-4.0 · pointer only · 8f49eb5b19d3ac4e · report fixture: signature gt:Tensor/1/int, pred:Tensor/1/int · returned float · level recorded 2026-09-24
compute_auprc src/codebase/metrics.py ran; the contract check could not run (RAISES) fingerprinted CC-BY-4.0 · pointer only · 896063eb2a6b5fdd · report fixture: signature gt:ndarray/1/int, pred:ndarray/1/float · returned float · level recorded 2026-09-24
custom_collate in 17 papers src/codebase/caption_images.py ran · our draft was wrong CC-BY-4.0 · pointer only · 0dbfc40c7885054d · report fixture: signature batch:list/1/tuple · returned tuple · level recorded 2026-09-24
generate_ds_last_layer_retrain src/codebase/mitigate_error_slices.py ran CC-BY-4.0 · pointer only · 8c7e7d4a40a6ed72 · report fixture: signature tr_df:DataFrame/0/?, test_df:DataFrame/0/?, clf_image_emb_path:str/0/str, batch_size:int/0/int, seed:int/0/int, n_samples:int/0/int, col_name_0:str/0/str, col_name_1:str/0/str · returned tuple · level recorded 2026-09-24
get_Paths src/codebase/utils.py ran · our draft was wrong CC-BY-4.0 · pointer only · 3b0e08bad449b6ab · report fixture: signature args:Args/0/? · returned tuple · level recorded 2026-09-24
get_device in 101 papers src/codebase/utils.py ran · our draft was wrong CC-BY-4.0 · pointer only · 45216ce5a16d2a2e · report fixture: signature args:Args/0/? · returned str · level recorded 2026-09-24
get_hypothesis_from_llama src/codebase/validate_error_slices_w_LLM.py ran CC-BY-4.0 · pointer only · 6af797ee849743d4 · report fixture: signature key:str/0/str, prompt:str/0/str · returned tuple · level recorded 2026-09-24
init_additional_info src/codebase/save_img_reps.py ran · our draft was wrong fingerprinted CC-BY-4.0 · pointer only · 2058541939bc9d91 · report fixture: signature dataset:str/0/str · returned dict · level recorded 2026-09-24
init_path src/codebase/learn_aligner.py ran CC-BY-4.0 · pointer only · 559c536421e60ded · report fixture: signature seed:int/0/int, clf_reps_path:str/0/str, clip_reps_path:str/0/str, save_path:str/0/str, dataset:str/0/str · returned tuple · level recorded 2026-09-24
load_model_with_retries src/codebase/caption_images.py ran CC-BY-4.0 · pointer only · 9d091c247f43d1f2 · report fixture: returned tuple · level recorded 2026-09-24
process_batch in 31 papers src/codebase/save_img_reps.py ran CC-BY-4.0 · pointer only · 2da591b7c5b0cc23 · report fixture: signature batch:tuple/1/Tensor, device:str/0/str, clf:dict/0/?, clip_model:dict/0/?, classifier_type:str/0/str, dataset:str/0/str · returned tuple · level recorded 2026-09-24
resize_and_encode_image src/codebase/caption_images_gpt_4.py ran · our draft was wrong CC-BY-4.0 · pointer only · 3a2653bc82bd52d6 · report fixture: signature image_path:str/0/str, size:tuple/1/int · returned str · level recorded 2026-09-24
stratified_sample in 10 papers src/codebase/utils.py ran CC-BY-4.0 · pointer only · b29a01fd0e697f3d · report fixture: signature df:DataFrame/0/?, n:int/0/int, label:str/0/str · returned DataFrame · level recorded 2026-09-24
update_additional_info src/codebase/save_img_reps.py ran CC-BY-4.0 · pointer only · 54000d2c28a0531d · report fixture: signature additional_info:dict/0/?, batch_info:dict/0/?, dataset:str/0/str · returned dict · level recorded 2026-09-24
caption_image src/codebase/caption_images_gpt_4.py unverified CC-BY-4.0 · pointer only · 4ffff391e5439ad1 · report
get_hypothesis_from_GPT src/codebase/validate_error_slices_w_LLM.py unverified CC-BY-4.0 · pointer only · 8c7dfc479e1f9844 · report

Tasks

AttributeClusteringImage ClassificationLanguage ModellingLarge Language ModelSlice Discovery

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