Papers › CLadder: Assessing Causal Reasoning in Language Models

CLadder: Assessing Causal Reasoning in Language Models

7 Dec 2023NeurIPS 2023 11arXiv:2312.04350archive 2025-07-28

Zhijing Jin, Yuen Chen, Felix Leeb, Luigi Gresele, Ojasv Kamal, Zhiheng Lyu, Kevin Blin, Fernando Gonzalez Adauto, Max Kleiman-Weiner, Mrinmaya Sachan, Bernhard Schölkopf

The ability to perform causal reasoning is widely considered a core feature of intelligence. In this work, we investigate whether large language models (LLMs) can coherently reason about causality. Much of the existing work in natural language processing (NLP) focuses on evaluating commonsense causal reasoning in LLMs, thus failing to assess whether a model can perform causal inference in accordance with a set of well-defined formal rules. To address this, we propose a new NLP task, causal inference in natural language, inspired by the "causal inference engine" postulated by Judea Pearl et al. We compose a large dataset, CLadder, with 10K samples: based on a collection of causal graphs and queries (associational, interventional, and counterfactual), we obtain symbolic questions and ground-truth answers, through an oracle causal inference engine. These are then translated into natural language. We evaluate multiple LLMs on our dataset, and we introduce and evaluate a bespoke chain-of-thought prompting strategy, CausalCoT. We show that our task is highly challenging for LLMs, and we conduct an in-depth analysis to gain deeper insights into the causal reasoning abilities of LLMs. Our data is open-sourced at https://huggingface.co/datasets/causalNLP/cladder, and our code can be found at https://github.com/causalNLP/cladder.

PaperPDFConference PDFCodeCode Syntology ranMethod as code

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 19 code samples harvested from 2 repositories linked to this paper: 15 ran (of which 1 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 10 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 10 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 18 samples from 1 repository, 14 ran (4 with no instrument failure; 10 where Syntology's instrument failed); community (archive-listed): 1 sample from 1 repository, 1 ran (1 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 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 15 samples that ran has no recorded date.

causalnlp/cladder officialmentioned in papermentioned on GitHubMITSyntology: 18 samples, 14 ran (10 instrument-failed) · 4 unverified report
strong-ai-lab/counterfactual-llm-inference mentioned on GitHubSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 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

19 samples harvested: 15 ran (of which 1 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 10 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
10ran · our draft was wrong
3ran
4unverified

Licence: 0 of the 19 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 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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.

causalnlp/cladder official repository 18 samples, 14 ran (10 instrument-failed) · 4 unverified
convert_to_norm causalbenchmark/eval/run_alpaca.py ran · honoured contract fingerprinted MIT (permissive) · a968c2f0fc097703 · report fixture: signature value:str/0/str · returned int · level recorded 2026-09-24
extract_summary_data causalbenchmark/generator.py ran · our draft was wrong MIT (permissive) · 1f6cf03d7898a1a8 · report fixture: signature data:list/1/dict, pbar:bool/0/bool · returned list · level recorded 2026-09-24
find_gold causalbenchmark/formatting.py ran MIT (permissive) · 50bbddac8ac5110e · report fixture: signature options:dict/0/?, num:int/0/int, rng:RandomState/0/? · returned tuple · level recorded 2026-09-24
format_prompt in 45 papers causalbenchmark/eval/generate_data_llama.py ran · our draft was wrong MIT (permissive) · a5a90249b782a1b6 · report fixture: signature datum:dict/0/?, system_prompt:str/0/str · returned str · level recorded 2026-09-24
generate_all_bit_strings causalbenchmark/util.py ran · honoured contract MIT (permissive) · 13efc95e9f29e8d6 · report fixture: signature n:int/0/int, dtype:callable/0/? · returned ndarray · level recorded 2026-09-24
generate_prompt in 110 papers causalbenchmark/eval/run_alpaca.py ran · our draft was wrong fingerprinted MIT (permissive) · d9793b16bbddeedb · report fixture: signature instruction:str/0/str, input_ctxt:str/0/str · returned str · level recorded 2026-09-24
generate_prompts in 9 papers causalbenchmark/eval/generate_data_llama.py ran · our draft was wrong MIT (permissive) · 9a82e2d14a589b26 · report fixture: signature data:list/1/dict, system_prompt:str/0/str · returned list · level recorded 2026-09-24
getOriginalDataset causalbenchmark/eval/eval_llms.py ran · our draft was wrong MIT (permissive) · df7bdd730e865d39 · report fixture: signature originalFile:str/0/str · returned DataFrame · level recorded, date not recorded
getOriginalDataset causalbenchmark/eval/eval_llms.py ran · our draft was wrong MIT (permissive) · 130d3a3bae1d92a1 · report fixture: signature originalFile:str/0/str · returned DataFrame · level recorded 2026-09-24
parse_given_info causalbenchmark/util.py ran · our draft was wrong MIT (permissive) · 94c9fff6118c5bb5 · report fixture: signature info:dict/0/? · returned list · level recorded 2026-09-24
parse_mechanism_str causalbenchmark/util.py ran · our draft was wrong fingerprinted MIT (permissive) · b5a6553f772f87db · report fixture: signature raw:str/0/str · returned tuple · level recorded 2026-09-24
read_data in 132 papers causalbenchmark/eval/generate_data_llama.py ran · our draft was wrong MIT (permissive) · 030aa16d0b1ec724 · report fixture: signature input_file:str/0/str · returned dict · level recorded 2026-09-24
sample_data_points causalbenchmark/eval/data_for_poster.py ran · our draft was wrong MIT (permissive) · 5bc9c80796cce905 · report fixture: signature file_path:str/0/str, num:int/0/int · returned str · level recorded 2026-09-24
tf_scorer causalbenchmark/eval/eval_for_poster.py ran fingerprinted MIT (permissive) · 2210535f064aacd1 · report fixture: signature pred:str/0/str, truth:str/0/str · returned int · level recorded 2026-09-24
eval_direct_dataset causalbenchmark/eval/eval_for_poster.py unverified MIT (permissive) · 39a599872519e96d · report
eval_graph_dataset causalbenchmark/eval/eval_for_poster.py unverified MIT (permissive) · f261606cedd728c1 · report
removeIDSNotReady causalbenchmark/eval/eval_llms.py unverified MIT (permissive) · 94cd3da8f74a72a2 · report
removeIDSNotReady causalbenchmark/eval/eval_llms.py unverified MIT (permissive) · d816d4383e5fec5d · report
strong-ai-lab/counterfactual-llm-inference community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
Query src/causal/counterfactual_inference.py ran · metamorphic tier: deterministic MIT (permissive) · f6b9303334b7eb26 · report fixture: returned Query · level recorded 2026-09-22

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for CAUSALCOT (graph method: CAUSALCOT). 1 brick; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

  1. Query entry · level 1 · ran · f6b9303334b7eb26

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2312.04350") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Causal InferenceCommonsense Causal Reasoning

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.

Methods

Causal inferenceSET

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