Papers › Ethical-Advice Taker: Do Language Models Understand Natural Language Interventions?

Ethical-Advice Taker: Do Language Models Understand Natural Language Interventions?

2 Jun 2021Findings (ACL) 2021 8arXiv:2106.01465archive 2025-07-28

Jieyu Zhao, Daniel Khashabi, Tushar Khot, Ashish Sabharwal, Kai-Wei Chang

Is it possible to use natural language to intervene in a model's behavior and alter its prediction in a desired way? We investigate the effectiveness of natural language interventions for reading-comprehension systems, studying this in the context of social stereotypes. Specifically, we propose a new language understanding task, Linguistic Ethical Interventions (LEI), where the goal is to amend a question-answering (QA) model's unethical behavior by communicating context-specific principles of ethics and equity to it. To this end, we build upon recent methods for quantifying a system's social stereotypes, augmenting them with different kinds of ethical interventions and the desired model behavior under such interventions. Our zero-shot evaluation finds that even today's powerful neural language models are extremely poor ethical-advice takers, that is, they respond surprisingly little to ethical interventions even though these interventions are stated as simple sentences. Few-shot learning improves model behavior but remains far from the desired outcome, especially when evaluated for various types of generalization. Our new task thus poses a novel language understanding challenge for the community.

PaperPDFConference PDFCodeCode 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 11 code samples harvested from 1 repository linked to this paper: 9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 11 samples from 1 repository, 9 ran (9 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 between 2026-09-25 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

allenai/ethical-interventions officialmentioned in paperpytorchApache-2.0Syntology: 11 samples, 9 ran (0 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

11 samples harvested: 9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 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 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.

9ran
2unverified

Licence: 0 of the 11 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 allenai/ethical-interventions. “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.

allenai/ethical-interventions official repository 11 samples, 9 ran (0 instrument-failed) · 2 unverified
cal_same get_acc.py ran Apache-2.0 (permissive) · 1dd8d8ccbcfefd0f · report fixture: signature golden:list/1/str, ans_q0:list/1/str · returned float · level recorded 2026-09-25
get_ans_p analysis.py ran Apache-2.0 (permissive) · 882df10f7336e7d9 · report fixture: signature ex:dict/0/?, qid:int/0/int · returned tuple · level recorded 2026-09-25
get_subj1_win_score analysis.py ran Apache-2.0 (permissive) · c60cab71350d2fbc · report fixture: signature spair:tuple/1/str, ex_pair:list/1/dict · returned float · level recorded 2026-09-25
get_tokens in 40 papers mutils.py ran Apache-2.0 (permissive) · db2b74b069046e20 · report fixture: signature encodings:dict/0/?, tokenizer:StandInTokenizer/0/? · returned list · level recorded 2026-09-25
pairup_ex analysis.py ran Apache-2.0 (permissive) · af5389807d8f56a5 · report fixture: signature data:dict/0/? · returned dict · level recorded 2026-09-25
pairup_ex ianalysis.py ran Apache-2.0 (permissive) · bda22be74de395aa · report fixture: signature preds:dict/0/? · returned dict · level recorded 2026-09-26
read_data in 132 papers mutils.py ran Apache-2.0 (permissive) · 53609984a77d7a10 · report fixture: signature path:str/0/str, count:int/0/int, replace2token:int/0/int · returned tuple · level recorded 2026-09-26
read_preds get_acc.py ran Apache-2.0 (permissive) · bf7715504cf7eafb · report fixture: signature file:str/0/str, ismale:int/0/int · returned tuple · level recorded 2026-09-25
read_squad mutils.py ran Apache-2.0 (permissive) · bf49efe2e2e2a978 · report fixture: signature path:str/0/str, count:int/0/int · returned tuple · level recorded 2026-09-26
get_data in 223 papers model_select.py unverified Apache-2.0 (permissive) · 0154494fec62dfcd · report
get_data in 223 papers plot.py unverified Apache-2.0 (permissive) · ae4db27c6dd3327c · report

Tasks

EthicsFew-Shot LearningQuestion AnsweringReading Comprehension

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