Papers › Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models...

Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Tasks

5 Jul 2023arXiv:2307.02477archive 2025-07-28

Zhaofeng Wu, Linlu Qiu, Alexis Ross, Ekin Akyürek, Boyuan Chen, Bailin Wang, Najoung Kim, Jacob Andreas, Yoon Kim

The impressive performance of recent language models across a wide range of tasks suggests that they possess a degree of abstract reasoning skills. Are these skills general and transferable, or specialized to specific tasks seen during pretraining? To disentangle these effects, we propose an evaluation framework based on "counterfactual" task variants that deviate from the default assumptions underlying standard tasks. Across a suite of 11 tasks, we observe nontrivial performance on the counterfactual variants, but nevertheless find that performance substantially and consistently degrades compared to the default conditions. This suggests that while current LMs may possess abstract task-solving skills to an extent, they often also rely on narrow, non-transferable procedures for task-solving. These results motivate a more careful interpretation of language model performance that teases apart these aspects of behavior.

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 15 code samples harvested from 1 repository linked to this paper: 13 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 1 where Syntology's instrument failed) · 2 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: 15 samples from 1 repository, 13 ran (12 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.

zhaofengwu/counterfactual-evaluation officialmentioned in papermentioned on GitHubMITSyntology: 15 samples, 13 ran (1 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

15 samples harvested: 13 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 1 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.

1ran · our draft was wrong
12ran
2unverified

Licence: 1 of the 15 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from zhaofengwu/counterfactual-evaluation. “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.

zhaofengwu/counterfactual-evaluation official repository 15 samples, 13 ran (1 instrument-failed) · 2 unverified
encode_images in 6 papers drawing/eval_utils.py ran MIT (permissive) · dd09dc3fabcd7c46 · report fixture: signature images:list/1/Tensor, processor:callable/0/?, model:callable/0/? · returned Tensor · level recorded 2026-09-24
escape in 10 papers arithmetic/query_ccc.py ran fingerprinted MIT (permissive) · 8e2c1bf8f5114da3 · report fixture: signature str:str/0/str · returned str · level recorded 2026-09-24
estimate_pass_at_k in 28 papers programming/generation/human_eval/evaluation.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · e080db2eaa81fdb3 · report fixture: signature num_samples:int/0/int, num_correct:ndarray/1/int, k:int/0/int · returned ndarray · level recorded 2026-09-22
get_captions drawing/eval_utils.py ran fingerprinted MIT (permissive) · 4fd941db8b2c2e88 · report fixture: signature obj:str/0/str · returned list · level recorded 2026-09-24
get_label in 36 papers arithmetic/sample.py ran MIT (permissive) · 6cd76a2436afdd9f · report fixture: signature expr:str/0/str, base:int/0/int · returned str · level recorded 2026-09-24
load_data in 700 papers chess/query.py ran MIT (permissive) · 819f8be42e847f42 · report fixture: signature data_file:str/0/str · returned list · level recorded 2026-09-24
parse_output in 21 papers arithmetic/eval_ccc.py ran fingerprinted MIT (permissive) · 5352f13bd6bc44b3 · report fixture: signature output:str/0/str · returned str · level recorded 2026-09-24
query_openai in 6 papers query_utils.py ran MIT (permissive) · 36f593974514e07c · report fixture: signature prompt:str/0/str, model_name:str/0/str, system_msg:str/0/str, history:list/1/dict, max_tokens:int/0/int, temperature:float/0/float, retry:int/0/int, n:int/0/int · returned coroutine · level recorded 2026-09-24
sample_number arithmetic/sample.py ran MIT (permissive) · 5aa746044ba7f7d5 · report fixture: signature n_digits:int/0/int, base:int/0/int · returned str · level recorded 2026-09-24
sample_single arithmetic/sample.py ran MIT (permissive) · dc7985be0af1dc39 · report fixture: signature n_digits:int/0/int, base:int/0/int · returned str · level recorded 2026-09-24
templatize arithmetic/query_ccc.py ran fingerprinted MIT (permissive) · 2c5dcccc856725c9 · report fixture: signature expr:str/0/str, base:int/0/int · returned str · level recorded 2026-09-24
templatize chess/query.py ran MIT (permissive) · 9639157e1c524625 · report fixture: signature mode:str/0/str, pgn_string:str/0/str, cot:bool/0/bool, is_control:bool/0/bool · returned str · level recorded 2026-09-24
unescape in 7 papers arithmetic/eval_ccc.py ran fingerprinted MIT (permissive) · 274b5d31316b3739 · report fixture: signature str:str/0/str · returned str · level recorded 2026-09-24
encode_classes drawing/eval_utils.py unverified MIT (permissive) · dd4aafd6d5e91a3c · report
load_data in 700 papers arithmetic/query.py unverified MIT (permissive) · 19996a3c6b913d67 · report

Tasks

Language ModelingLanguage Modelling

1 archive task tag without a task page not shown.

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