Papers › Attention Satisfies: A Constraint-Satisfaction Lens on Factual Errors of Language Models
Attention Satisfies: A Constraint-Satisfaction Lens on Factual Errors of Language Models
Mert Yuksekgonul, Varun Chandrasekaran, Erik Jones, Suriya Gunasekar, Ranjita Naik, Hamid Palangi, Ece Kamar, Besmira Nushi
We investigate the internal behavior of Transformer-based Large Language Models (LLMs) when they generate factually incorrect text. We propose modeling factual queries as constraint satisfaction problems and use this framework to investigate how the LLM interacts internally with factual constraints. We find a strong positive relationship between the LLM's attention to constraint tokens and the factual accuracy of generations. We curate a suite of 10 datasets containing over 40,000 prompts to study the task of predicting factual errors with the Llama-2 family across all scales (7B, 13B, 70B). We propose SAT Probe, a method probing attention patterns, that can predict factual errors and fine-grained constraint satisfaction, and allow early error identification. The approach and findings take another step towards using the mechanistic understanding of LLMs to enhance their reliability.
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):
get_harvested_code_for_paper(arxiv_id="2309.15098")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="2309.15098", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="2309.15098")
Code
Syntology 11 code samples: 10 from 1 repository linked to this paper, 1 identical to code harvested from another paper's repository. Across all 11: 7 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.
By repository: official repository: 10 samples from 1 repository, 6 ran (2 with no instrument failure; 4 where Syntology's instrument failed); 1 identical to code first harvested elsewhere. 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 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 7 samples that ran has no recorded date.
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: 7 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 5 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 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.
Licence: 11 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 microsoft/mechanistic-error-probe. 1 sample is listed last, in a group without a repository. “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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.
d350af5b5c8ee615 · report
fixture: returned StopForward · level recorded 2026-09-22 56d9c31f9a8ddc6d · report
fixture: signature sl:list/1/int, l:list/1/int, offset:int/0/int · returned tuple · level recorded 2026-09-22 4546d6be91afba23 · report
fixture: signature prompt:str/0/str, parts:list/1/str, tokenizer:SimpleTokenizer/0/? · returned list · level recorded 2026-09-22 90cd8804aa1b1e64 · report
fixture: signature fn:callable/0/?, args:tuple/1/int, kwargs:dict/0/? · returned tuple · level recorded 2026-09-22 89c23643de6b387c · report
fixture: signature x:dict/0/?, clone:bool/0/bool, detach:bool/0/bool, retain_grad:bool/0/bool · returned dict · level recorded 2026-09-22 census: 15 implementations from 60 papers, 2 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 4, kind float, dtype float32 model_lib/attention_tools.py ran; the contract check could not run (RAISES) fingerprinted licence not identified · pointer only ·
3281dccd4fa39596 · report
fixture: signature hidden_states:Tensor/4/float, n_rep:int/0/int · returned Tensor · level recorded 2026-09-22 0aeb158b537a2630 · report
8717ccf6ff080a13 · report
4d46774ab77c1ff3 · report
4c40a34cc6ec66e9 · report
1 sample is identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
8953f9ef90cf6afd · report
fixture: signature model:callable/0/?, name:str/0/str · returned Linear · level recorded, date not recorded 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 SAT Probe (graph method: SAT Probe). 10 bricks; individually on a fixture: 7 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.
- run_attention_monitor entry · level 0 · unverified ·
4c40a34cc6ec66e9 - TraceDict helper · level 0 · unverified ·
8717ccf6ff080a13 - find_within_text helper · level 1 · ran · honoured contract ·
4546d6be91afba23 - repeat_kv helper · level 1 · ran; the contract check could not run (RAISES) ·
3281dccd4fa39596 - StopForward helper · level 1 · ran ·
d350af5b5c8ee615 - Trace helper · level 0 · unverified ·
0aeb158b537a2630 - find_sub_list helper · level 1 · ran; the contract check could not run (RAISES) ·
56d9c31f9a8ddc6d - get_module helper · level 1 · ran · our draft was wrong ·
8953f9ef90cf6afd - invoke_with_optional_args helper · level 1 · ran · our draft was wrong ·
90cd8804aa1b1e64 - recursive_copy helper · level 1 · ran · our draft was wrong ·
89c23643de6b387c
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="2309.15098") returns these assemblies with each brick's role and wiring (how to connect).
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