SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.11683 · ACL · 2024

ne Prompt To Rule Them All: LLMs for Opinion Summary Evaluation

Pushpak Bhattacharyya, Tejpalsingh Siledar, Nikesh Garera, Suman Banerjee, Amey Patil, Sudhanshu Shekhar, Rupasai Rangaraju, Swaprava Nath, Swaroop Nath, Sri Raghava

arXiv · PDF · Open in the Atlas

Code that ran

5 of 5 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 5 failures of our instrument; 0 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2402.11683.json · badge: /api/ran/2402.11683.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
tjsiledar/SummEval-OP canonical (classifier label)
classifier basis: census
5 ran · 0 no recorded run
FunctionStatusWhere it lives
convert_ast Ran
ran; our contract draft was wrong, not the code
tjsiledar/SummEval-OP/code/compute_correlation.py
code served (permissive licence) · get_code("a09f1d2d5625b3c4")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned dict. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import ast

# convert_ast takes a single parameter 'row' and calls ast.literal_eval on it
# ast.literal_eval safely evaluates a string containing a Python literal
# We need to provide a string representation of a Python literal

ARGS = {
    "row": "{'key': 'value', 'number': 42, 'list': [1, 2, 3]}"
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
extract_scores Ran
ran; our contract draft was wrong, not the code
tjsiledar/SummEval-OP/code/efficient-evaluator-v2.py
code served (permissive licence) · get_code("462312c0339acd23")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned list. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import re

def extract_scores(texts):
    return_scores = []
    for text in texts:
        temp = []
        for t in text:
            pattern = '<score>(\\d+)</score>'
            scores = re.findall(pattern, t)
            scores = [int(score) for score in scores]
            temp.append(scores)
        return_scores.append(temp)
    return return_scores

ARGS = {
    'texts': [
        [
            '<score>42</score> some text <score>87</score>',
            'no scores here',
            '<score>15</score>'
        ],
        [
            '<score>100</score>',
            '<score>5</score> and <score>20</score>',
        ]
    ]
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list — a list output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
extract_text Ran
ran; our contract draft was wrong, not the code
tjsiledar/SummEval-OP/code/efficient-evaluator-v2.py
code served (permissive licence) · get_code("f55db2ffc45ecfd2")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned list. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

class MockOutput:
    def __init__(self, text):
        self.text = text

class MockOutputContainer:
    def __init__(self, outputs):
        self.outputs = outputs

# Create mock outputs with text
output1 = MockOutputContainer([
    MockOutput("hello world"),
    MockOutput("foo bar")
])

output2 = MockOutputContainer([
    MockOutput("test text"),
    MockOutput("another example"),
    MockOutput("final output")
])

outputs = [output1, output2]

ARGS = {
    "outputs": outputs
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list — a list output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
frequency_calculation Ran
ran; our contract draft was wrong, not the code
tjsiledar/SummEval-OP/code/compute_correlation.py
code served (permissive licence) · get_code("96e703950dc09e13")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned dict. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

torch.manual_seed(0)

score_list = [1, 2, 3, 4, 5, 1, 2, 3, 1, 4, 5, 5, 2]

ARGS = {
    "score_list": score_list
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
probability_calculation Ran
ran; our contract draft was wrong, not the code
tjsiledar/SummEval-OP/code/compute_correlation.py
code served (permissive licence) · get_code("b38fef96c251b1de")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# The function probability_calculation takes a score_list parameter
# It calls frequency_calculation on it, which iterates through elements
# and increments counters for keys 1-5, so score_list should contain
# integers from 1 to 5

score_list = [1, 2, 3, 4, 5, 1, 2, 3, 1, 5]

ARGS = {
    "score_list": score_list
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, dtype family float — a tuple output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 5 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Evaluation of opinion summaries using conventional reference-based metrics often fails to provide a comprehensive assessment and exhibits limited correlation with human judgments. While Large Language Models (LLMs) have shown promise as reference-free metrics for NLG evaluation, their potential remains unexplored for opinion summary evaluation. Furthermore, the absence of sufficient opinion summary evaluation datasets hinders progress in this area. In response, we introduce the SUMMEVAL-OP dataset, encompassing 7 dimensions crucial to the evaluation of opinion summaries: fluency, coherence, relevance, faithfulness, aspect coverage, sentiment consistency, and specificity. We propose OP-I-PROMPT, a dimension-independent prompt, along with OP-PROMPTS, a dimension-dependent set of prompts for opinion summary evaluation. Our experiments demonstrate that OP-I-PROMPT emerges as a good alternative for evaluating opinion summaries, achieving an average Spearman correlation of 0.70 with human judgments, surpassing prior methodologies. Remarkably, we are the first to explore the efficacy of LLMs as evaluators, both on closed-source and open-source models, in the opinion summary evaluation domain.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2402.11683")
get_code_for_paper("2402.11683")
have("2402.11683")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2402.11683.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2402.11683.svg)](https://syntology.ai/paper/2402.11683)

Connect an agent — have() is free.