SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2401.06532 · ACL · 2024

INTERS: Unlocking the Power of Large Language Models in Search with Instruction Tuning

Ji-Rong Wen, Zheng Liu, Zhicheng Dou, Yutao Zhu, Chenghao Zhang, Peitian Zhang, Yifei Chen, Binyu Xie

arXiv · PDF · Open in the Atlas

Code that ran

4 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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 3 failures of our instrument; 1 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/2401.06532.json · badge: /api/ran/2401.06532.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
DaoD/INTERS canonical (classifier label)
classifier basis: census
4 ran · 1 no recorded run
FunctionStatusWhere it lives
get_max_length_in_nested_lists Ran
ran, honoured the contract we drafted
DaoD/INTERS/evaluation/qdu-tasks/src/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from Clement25/SharedLLM, is pointer only (licence: NONE) · get_code("74dab428120d8998")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from Clement25/SharedLLM, and GitHub detected no licence in that repository 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.

makedirs Ran
ran; our contract draft was wrong, not the code
DaoD/INTERS/evaluation/qdu-tasks/src/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from EIT-NLP/ReCache, is pointer only (licence: NONE) · get_code("df02a4d06d5ad0f2")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from EIT-NLP/ReCache, and GitHub detected no licence in that repository 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_file_dir_name_ext Ran
ran; our contract draft was wrong, not the code
DaoD/INTERS/evaluation/qdu-tasks/src/utils.py
code served (permissive licence) · get_code("09c88bc1a2c9564a")
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 pathlib
import tempfile
import os

# Create a temporary directory and file for testing
temp_dir = tempfile.mkdtemp()
test_file_path = os.path.join(temp_dir, "example_file.txt")

# Create the test file
with open(test_file_path, 'w') as f:
    f.write("test content")

ARGS = {
    "path": test_file_path
}
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 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
truncate Ran
ran; our contract draft was wrong, not the code
DaoD/INTERS/evaluation/qdu-tasks/eval_rerank.py
code served (permissive licence) · get_code("5cf8f57b0919504b")
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 str. 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
from transformers import AutoTokenizer

torch.manual_seed(0)

# Create a minimal tokenizer-like object
class MinimalTokenizer:
    def __init__(self):
        self.vocab = {
            "<unk>": 0,
            "hello": 1,
            "world": 2,
            "test": 3,
            "text": 4,
            "[CLS]": 5,
            "[SEP]": 6,
        }
        self.id_to_token = {v: k for k, v in self.vocab.items()}
    
    def encode(self, text, add_special_tokens=False, max_length=None, truncation=False):
        # Simple tokenization: split by spaces and map to token ids
        tokens = text.lower().split()
        token_ids = [self.vocab.get(token, 0) for token in tokens]
        
        if truncation and max_length is not None:
            token_ids = token_ids[:max_length]
        
        return token_ids
    
    def decode(self, token_ids):
        # Convert token ids back to text
        tokens = [self.id_to_token.get(tid, "<unk>") for tid in token_ids]
        return " ".join(tokens)

# Create tokenizer instance
tokenizer = MinimalTokenizer()

# Define arguments
ARGS = {
    "text": "hello world test",
    "tokenizer": tokenizer,
    "max_length": 10
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, transformers — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
get_model_and_tokenizer Not yet run
unverified (harvested, no recorded run)
DaoD/INTERS/evaluation/qdu-tasks/src/modeling.py
code served (permissive licence) · get_code("a5ceb4dcfea73278")
How it ran

no invocation recorded.

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, 2 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 2 later) and 3 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
get_max_length_in_nested_lists 1 other paper
1 later
2603.04759 (2026-03)
Stacked from One: Multi-Scale Self-Injection for Context Window Extension
makedirs 1 other paper
1 later
2608.19662 (2026-08)
ReCache: Efficient KV Cache Reuse and Compression for Tool-Augmented LLM Agents

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

Large language models (LLMs) have demonstrated impressive capabilities in various natural language processing tasks. Despite this, their application to information retrieval (IR) tasks is still challenging due to the infrequent occurrence of many IR-specific concepts in natural language. While prompt-based methods can provide task descriptions to LLMs, they often fall short in facilitating a comprehensive understanding and execution of IR tasks, thereby limiting LLMs' applicability. To address this gap, in this work, we explore the potential of instruction tuning to enhance LLMs' proficiency in IR tasks. We introduce a novel instruction tuning dataset, INTERS, encompassing 20 tasks across three fundamental IR categories: query understanding, document understanding, and query-document relationship understanding. The data are derived from 43 distinct datasets with manually written templates. Our empirical results reveal that INTERS significantly boosts the performance of various publicly available LLMs, such as LLaMA, Mistral, and Falcon, in IR tasks. Furthermore, we conduct extensive experiments to analyze the effects of instruction design, template diversity, few-shot demonstrations, and the volume of instructions on performance. We make our dataset and the fine-tuned models publicly accessible at https: //github.com/DaoD/INTERS.

For agents

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

get_harvested_code_for_paper("2401.06532")
get_code_for_paper("2401.06532")
have("2401.06532")

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

curl https://syntology.ai/api/ran/2401.06532.json

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

[![Syntology run record](https://syntology.ai/api/ran/2401.06532.svg)](https://syntology.ai/paper/2401.06532)

Connect an agent — have() is free.