Papers › Eliciting Informative Text Evaluations with Large Language Models

Eliciting Informative Text Evaluations with Large Language Models

23 May 2024arXiv:2405.15077archive 2025-07-28

Yuxuan Lu, Shengwei Xu, Yichi Zhang, Yuqing Kong, Grant Schoenebeck

Peer prediction mechanisms motivate high-quality feedback with provable guarantees. However, current methods only apply to rather simple reports, like multiple-choice or scalar numbers. We aim to broaden these techniques to the larger domain of text-based reports, drawing on the recent developments in large language models. This vastly increases the applicability of peer prediction mechanisms as textual feedback is the norm in a large variety of feedback channels: peer reviews, e-commerce customer reviews, and comments on social media. We introduce two mechanisms, the Generative Peer Prediction Mechanism (GPPM) and the Generative Synopsis Peer Prediction Mechanism (GSPPM). These mechanisms utilize LLMs as predictors, mapping from one agent's report to a prediction of her peer's report. Theoretically, we show that when the LLM prediction is sufficiently accurate, our mechanisms can incentivize high effort and truth-telling as an (approximate) Bayesian Nash equilibrium. Empirically, we confirm the efficacy of our mechanisms through experiments conducted on two real datasets: the Yelp review dataset and the ICLR OpenReview dataset. We highlight the results that on the ICLR dataset, our mechanisms can differentiate three quality levels -- human-written reviews, GPT-4-generated reviews, and GPT-3.5-generated reviews in terms of expected scores. Additionally, GSPPM penalizes LLM-generated reviews more effectively than GPPM.

PaperPDFCodeCode 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.

Syntology holds a reference implementation of Generative Synopsis Peer Prediction Mechanism (GSPPM), generated from the paper text (not the authors' code), at level 2 on Syntology's ladder: V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)” (quoted from Syntology's server card). No rung compares this code against the authors' implementation. For agents: get_reference_implementation(name='Generative Synopsis Peer Prediction Mechanism (GSPPM)') (how to connect); the free check have('2405.15077') needs no token.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 14 code samples harvested from 1 repository linked to this paper: 10 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 8 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 8 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 14 samples from 1 repository, 10 ran (2 with no instrument failure; 8 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. 2 of the 10 samples that ran have no recorded date.

yx-lu/eliciting-informative-text-evaluations-with-large-language-models officialmentioned in paperpytorchCC-BY-4.0Syntology: 14 samples, 10 ran (8 instrument-failed) · 4 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

14 samples harvested: 10 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 8 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.

1ran · honoured contract
8ran · our draft was wrong
1ran
4unverified

Licence: 14 of the 14 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 yx-lu/eliciting-informative-text-evaluations-with-large-language-models. “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.

yx-lu/eliciting-informative-text-evaluations-with-large-language-models official repository 14 samples, 10 ran (8 instrument-failed) · 4 unverified
extract_element_text pdf_management/pdfparser.py ran · our draft was wrong CC-BY-4.0 · pointer only · 90432c0bdc5cd3dd · report fixture: signature element:Element/0/? · returned str · level recorded 2026-09-24
fetch_from_cache experiments/utils.py ran · our draft was wrong fingerprinted CC-BY-4.0 · pointer only · 5a1a20f1d1feda8f · report fixture: signature cache_key:str/0/str, cache_dir:str/0/str · returned dict · level recorded 2026-09-24
gen_two_pos experiments/baseline.py ran · honoured contract fingerprinted CC-BY-4.0 · pointer only · 769e6af963c596c3 · report fixture: signature l:int/0/int · returned tuple · level recorded 2026-09-24
generate_cache_key experiments/utils.py ran · our draft was wrong CC-BY-4.0 · pointer only · a98a2c012cac1092 · report fixture: signature params:dict/0/? · returned str · level recorded 2026-09-24
get_article_title pdf_management/pdfparser.py ran · our draft was wrong CC-BY-4.0 · pointer only · 3b43b1aabeb844e6 · report fixture: signature root:Element/0/? · returned str · level recorded 2026-09-24
get_section_text pdf_management/pdfparser.py ran · our draft was wrong CC-BY-4.0 · pointer only · b68c58dce0510cc0 · report fixture: signature root:Element/0/?, section_title:str/0/str · returned str · level recorded 2026-09-24
parse_review_summary experiments/direct.py ran · our draft was wrong fingerprinted CC-BY-4.0 · pointer only · 6c4e4df7a400e23a · report fixture: signature summary:str/0/str · returned str · level recorded, date not recorded
remove_half_lines experiments/direct.py ran · our draft was wrong fingerprinted CC-BY-4.0 · pointer only · d6b82917310bb5fd · report fixture: signature summary:str/0/str · returned str · level recorded, date not recorded
save_to_cache experiments/utils.py ran CC-BY-4.0 · pointer only · 3baf07c6128dd911 · report fixture: signature cache_key:str/0/str, response:dict/0/?, cache_dir:str/0/str, overwrite:bool/0/bool · returned dict · level recorded 2026-09-24
to_ascii openreview/gen_dataset.py ran · our draft was wrong fingerprinted CC-BY-4.0 · pointer only · 6eb67df219b6a1f1 · report fixture: signature input_str:str/0/str · returned str · level recorded 2026-09-24
get_iclr2020_reviews openreview/crawl.py unverified CC-BY-4.0 · pointer only · 1112623cc2238462 · report
get_pridiction_score experiments/direct.py unverified CC-BY-4.0 · pointer only · f4c891c85cf99011 · report
get_review_summary experiments/direct.py unverified CC-BY-4.0 · pointer only · bf386b23c0697873 · report
get_score in 56 papers experiments/baseline.py unverified CC-BY-4.0 · pointer only · fc5eb58baae10b8a · report

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. For a generated assembly, an independent peer is a second implementation generated separately from the same paper text; neither implementation read the authors' code. At level 2 the two agreed numerically on the fixture's inputs; level 3 is recorded when property tests derived from the paper also passed on both, and each level 3 card prints how many its report lists. 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. A generated assembly's label was set when its code was generated for the method, and no model judged it; its card prints it as "by construction" or "not judged by a model". Where an assembly's phrase has no constructed figure, a brick that ran is not among the harvested samples this build reads, and whether a brick's run only constructed an object is read from that brick's harvested sample, so the figure was not counted; it does not say there were none.

2 assemblies on this paper: 1 harvested, 1 generated.

generated Assembly for Generative Synopsis Peer Prediction Mechanism (GSPPM) (graph method: Generative Synopsis Peer Prediction Mechanism (GSPPM)), generated from the paper text, not the repository's code. 1 brick; individually on a fixture: 1 ran (0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. Ran end-to-end against an independent peer (level 2).

label matches by construction: the code was generated for this method (not judged by a model)

  1. cluster_peer_prediction_score entry · level 2 · ran · our draft was wrong · b1f4344641dee8d7d628852f3129cd52e8baef5ac711432eacdc32adb5aaa404

harvested Assembly for Generative Peer Prediction Mechanism (GPPM) (graph method: Generative Peer Prediction Mechanism (GPPM)). 1 brick; individually on a fixture: 0 ran · 1 unverified. The assembly has not been run end-to-end.

  1. get_pridiction_score entry · level 0 · unverified · f4c891c85cf99011

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="2405.15077") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Multiple-choicePrediction

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AdamAttentionAttention DropoutBPECosine AnnealingDense ConnectionsDropoutGPT-3Layer NormalizationLinear LayerLinear Warmup With Cosine AnnealingMulti-Head AttentionResidual ConnectionSoftmaxWeight Decay

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