SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2607.08540 · 2026

Improving Ad-hoc Search Effectiveness for Conversational Information Retrieval via Model Merging

Jose Moreno, Lynda Tamine, Ahmed Kebir

arXiv · PDF · Open in the Atlas

Code that ran

11 of 13 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 1 has no contract verdict; 10 failures of our instrument; 2 no recorded run), measured 2026-11-22; 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/2607.08540.json · badge: /api/ran/2607.08540.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
fengranMark/QRACDR canonical (classifier label)
classifier basis: census
11 ran · 2 no recorded run
FunctionStatusWhere it lives
GetProcessingFn Ran
ran; our contract draft was wrong, not the code
fengranMark/QRACDR/index/gen_doc_embeddings.py
pointer only (licence: NONE) · get_code("8401ea37bd6f2579")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, fengranMark/QRACDR 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.

PassagePreprocessingFn Ran
ran; our contract draft was wrong, not the code
fengranMark/QRACDR/index/gen_tokenized_doc.py
pointer only (licence: NONE) · get_code("26deee1ffdfe9f35")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, fengranMark/QRACDR 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.

QueryPreprocessingFn Ran
ran; our contract draft was wrong, not the code
fengranMark/QRACDR/index/gen_tokenized_doc.py
pointer only (licence: NONE) · get_code("7b35e59c7f45e0fc")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, fengranMark/QRACDR 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.

cal_kd_loss Ran
ran; our contract draft was wrong, not the code
fengranMark/QRACDR/src/train_QRACDR.py
pointer only (licence: NONE) · get_code("9a17c22d15cfd8be")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, fengranMark/QRACDR 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.

load_collection Ran
ran on a synthesized input
fengranMark/QRACDR/src/utils.py
pointer only (licence: NONE) · get_code("f20c78e709caa7fa")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, fengranMark/QRACDR 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.

modify_neg_docs Ran
ran; our contract draft was wrong, not the code
fengranMark/QRACDR/preprocess/preprocess_topiocqa.py
pointer only (licence: NONE) · get_code("dadba3a20f2151cc")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, fengranMark/QRACDR 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.

modify_pos_docs Ran
ran; our contract draft was wrong, not the code
fengranMark/QRACDR/preprocess/preprocess_topiocqa.py
pointer only (licence: NONE) · get_code("08793fb12b976418")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, fengranMark/QRACDR 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.

pad_input_ids Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
fengranMark/QRACDR/index/gen_tokenized_doc.py
pointer only (licence: NONE) · get_code("b201d8d93b242b70")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, fengranMark/QRACDR 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.

padding_seq_to_same_length Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
fengranMark/QRACDR/src/data.py
pointer only (licence: NONE) · get_code("58745a56a67a45ad")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, fengranMark/QRACDR 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.

pload Ran
ran; our contract draft was wrong, not the code
fengranMark/QRACDR/src/utils.py
pointer only (licence: NONE) · get_code("4244b1c4f07c6819")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, fengranMark/QRACDR 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.

split_and_padding_neighbor Ran
ran; our contract draft was wrong, not the code
fengranMark/QRACDR/src/utils.py
pointer only (licence: NONE) · get_code("bcc8d91ab4ec9700")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, fengranMark/QRACDR 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.

cal_ranking_loss Not yet run
unverified (harvested, no recorded run)
fengranMark/QRACDR/src/train_QRACDR.py
pointer only (licence: NONE) · get_code("f0076b71c838d87b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, fengranMark/QRACDR 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_ranking_oracle_loss Not yet run
unverified (harvested, no recorded run)
fengranMark/QRACDR/src/train_QRACDR.py
pointer only (licence: NONE) · get_code("0d01fa6ed9029c43")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, fengranMark/QRACDR 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 13 samples lifted from this paper's linked repositories, 13 carry a function identity and 0 do not. Of the 13 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 0 later) and 10 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
pad_input_ids 2 other papers
2 dated earlier
2110.05789 (2021-10)
Learning Discrete Representations via Constrained Clustering for Effective and Efficient Dense Retrieval
2112.09118 (2021-12)
Unsupervised Dense Information Retrieval with Contrastive Learning
padding_seq_to_same_length 1 other paper
1 dated earlier
2601.09028 (2026-01)
OpenDecoder: Open Large Language Model Decoding to Incorporate Document Quality in RAG
pload 1 other paper
1 dated earlier
2601.09028 (2026-01)
OpenDecoder: Open Large Language Model Decoding to Incorporate Document Quality in RAG

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

Conversational information retrieval is challenging since it requires the consideration of the conversation history which potentially gives rise to topic shifts and coreference resolution across previous turns. To address these challenges, previous work mainly rely on traditional fine-tuning of ad-hoc retrievers on conversational datasets or extrapolates their generalizability through multi-tasking. However, this mainstream approach is costly-since it requires model re-training-and exhibits catastrophic forgetting, where the model loses its foundational ad-hoc retrieval performance. In this paper, we fill this gap by introducing model merging as a trainingfree strategy enabling the design of a single retrieval model that operates across both ad-hoc and conversational settings with no additional fine-tuning. We conduct experiments using linear and non-linear parameter-wise merging strategies-namely Model Soup and Slerp-on standard ad-hoc search and conversational retrieval datasets. Our results demonstrate that model merging significantly enhances the ad-hoc search capabilities of conversational retrievers while improving generalizability across task-specific datasets, achieving up to 15% higher NDCG@3 under zero-shot conditions. • Information systems → Information Retrieval.

For agents

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

get_harvested_code_for_paper("2607.08540")
get_code_for_paper("2607.08540")
have("2607.08540")

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

curl https://syntology.ai/api/ran/2607.08540.json

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

[![Syntology run record](https://syntology.ai/api/ran/2607.08540.svg)](https://syntology.ai/paper/2607.08540)

Connect an agent — have() is free.