SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.12052 · ACL · 2024

Small Models, Big Insights: Leveraging Slim Proxy Models to Decide When and What to Retrieve for LLMs

Ji-Rong Wen, Kun Fang, Zhicheng Dou, Yutao Zhu, Peidong Guo, Jiejun Tan

arXiv · PDF · Open in the Atlas

Code that ran

6 of 15 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; 2 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 4 failures of our instrument; 9 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/2402.12052.json · badge: /api/ran/2402.12052.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
plageon/slimplm canonical (classifier label)
classifier basis: census
6 ran · 9 no recorded run
FunctionStatusWhere it lives
exact_match_score Ran
ran, honoured the contract we drafted
plageon/slimplm/SKR/skr.py
pointer only (licence: NONE) · get_code("0be284da9bf9ca86")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, plageon/slimplm when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

f1_score Ran
ran, honoured the contract we drafted
plageon/slimplm/SKR/skr.py
pointer only (licence: NONE) · get_code("42ae926df6227a65")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, plageon/slimplm when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_stop_words_ids Ran
ran; our contract draft was wrong, not the code
plageon/slimplm/SKR/vllm_wrapper.py
pointer only (licence: NONE) · get_code("1616f54ad713d861")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, plageon/slimplm when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

make_context Ran
ran; our contract draft was wrong, not the code
plageon/slimplm/SKR/vllm_wrapper.py
pointer only (licence: NONE) · get_code("cc910a23dfa4faf9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, plageon/slimplm when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

normalize_answer Ran
ran; our contract draft was wrong, not the code
plageon/slimplm/SKR/skr.py
pointer only (licence: NONE) · get_code("ae914f80513baf0f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, plageon/slimplm when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

parse_query_rewrite_result Ran
ran; our contract draft was wrong, not the code
plageon/slimplm/itergen/itergen_search.py
pointer only (licence: NONE) · get_code("4559d324e8869534")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, plageon/slimplm when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

apply_retrieval Not yet run
unverified (harvested, no recorded run)
plageon/slimplm/itergen/itergen_search.py
pointer only (licence: NONE) · get_code("0d1849e93ded0365")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, plageon/slimplm when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

cal_logits Not yet run
unverified (harvested, no recorded run)
plageon/slimplm/flare/flare_search.py
pointer only (licence: NONE) · get_code("24880d8347224f43")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, plageon/slimplm when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

chat_prompt_search Not yet run
unverified (harvested, no recorded run)
plageon/slimplm/itergen/itergen_chat.py
pointer only (licence: NONE) · get_code("b15ebcca575175b2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, plageon/slimplm when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

check_chat_result Not yet run
unverified (harvested, no recorded run)
plageon/slimplm/flare/flare_search.py
pointer only (licence: NONE) · get_code("9264b80c05ab8367")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, plageon/slimplm when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

first_round_inference_req Not yet run
unverified (harvested, no recorded run)
plageon/slimplm/flare/flare_chat_inference.py
pointer only (licence: NONE) · get_code("017881a697f8102f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, plageon/slimplm when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

get_dataset Not yet run
unverified (harvested, no recorded run)
plageon/slimplm/user_intent/finetune_llm.py
pointer only (licence: NONE) · get_code("a49b2e989e8da871")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, plageon/slimplm when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

sending_inference_request Not yet run
unverified (harvested, no recorded run)
plageon/slimplm/SKR/icl.py
pointer only (licence: NONE) · get_code("e6dea7666ba5f046")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, plageon/slimplm when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

sending_inference_request Not yet run
unverified (harvested, no recorded run)
plageon/slimplm/cot/cot_prompt_inference.py
pointer only (licence: NONE) · get_code("41b5dc31cd322ee3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, plageon/slimplm when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

sending_rewrite_request Not yet run
unverified (harvested, no recorded run)
plageon/slimplm/itergen/itergen_search.py
pointer only (licence: NONE) · get_code("b3e3436d21b2bc92")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, plageon/slimplm when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 15 samples lifted from this paper's linked repositories, 15 carry a function identity and 0 do not. Of the 15 distinct functions with an identity, 4 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 1 the same month, 3 later) and 11 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.

FunctionAlso present inEarliest-datedOthers named
f1_score 41 other papers
34 dated earlier, 2 the same month, 5 later
1508.06615 (2015-08)
Character-Aware Neural Language Models
1606.05250 (2016-06)
SQuAD: 100,000+ Questions for Machine Comprehension of Text
1608.07905 (2016-08)
Machine Comprehension Using Match-LSTM and Answer Pointer
and 38 more not named here
exact_match_score 1 other paper
1 later
2609.00513 (2026-09)
ISO-RAG: Isoperimetric Noise Control for Retrieval-Augmented Generation
get_stop_words_ids 1 other paper
1 dated earlier
2309.16609 (2023-09)
Qwen Technical Report
normalize_answer 1 other paper
1 later
2403.06840 (2024-03)
RA-ISF: Learning to Answer and Understand from Retrieval Augmentation via Iterative Self-Feedback

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

The integration of large language models (LLMs) and search engines represents a significant evolution in knowledge acquisition methodologies. However, determining the knowledge that an LLM already possesses and the knowledge that requires the help of a search engine remains an unresolved issue. Most existing methods solve this problem through the results of preliminary answers or reasoning done by the LLM itself, but this incurs excessively high computational costs. This paper introduces a novel collaborative approach, namely SlimPLM, that detects missing knowledge in LLMs with a slim proxy model, to enhance the LLM's knowledge acquisition process. We employ a proxy model which has far fewer parameters, and take its answers as heuristic answers. Heuristic answers are then utilized to predict the knowledge required to answer the user question, as well as the known and unknown knowledge within the LLM. We only conduct retrieval for the missing knowledge in questions that the LLM does not know. Extensive experimental results on five datasets with two LLMs demonstrate a notable improvement in the end-to-end performance of LLMs in question-answering tasks, achieving or surpassing current state-of-the-art models with lower LLM inference costs. 1 * This work was done when Jiejun Tan was doing internship at Baichuan Intelligent Technology.

For agents

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

get_harvested_code_for_paper("2402.12052")
get_code_for_paper("2402.12052")
have("2402.12052")

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

curl https://syntology.ai/api/ran/2402.12052.json

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

[![Syntology run record](https://syntology.ai/api/ran/2402.12052.svg)](https://syntology.ai/paper/2402.12052)

Connect an agent — have() is free.