SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2405.05008 · EMNLP · 2024

ADELIE: Aligning Large Language Models on Information Extraction

Hao Peng, Juanzi Li, Lei Hou, Xiaozhi Wang, Yunjia Qi

arXiv · PDF · Open in the Atlas

Code that ran

15 of 18 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; 14 failures of our instrument; 3 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/2405.05008.json · badge: /api/ran/2405.05008.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
THU-KEG/ADELIE canonical (classifier label)
classifier basis: census
15 ran · 3 no recorded run
FunctionStatusWhere it lives
concatenated_forward Ran
ran; our contract draft was wrong, not the code
THU-KEG/ADELIE/train4llama/open_instruct/dpo_utils.py
pointer only (licence: NONE); the stored copy get_code serves, from luckyyysta/fine-grained-attribution, is pointer only (licence: NONE) · get_code("bd6665195c202c96")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, THU-KEG/ADELIE 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.

concatenated_inputs Ran
ran; our contract draft was wrong, not the code
THU-KEG/ADELIE/train4llama/open_instruct/dpo_utils.py
pointer only (licence: NONE); the stored copy get_code serves, from luckyyysta/fine-grained-attribution, is pointer only (licence: NONE) · get_code("98be928ee5a8a3bd")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, THU-KEG/ADELIE 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.

convert_message Ran
ran; our contract draft was wrong, not the code
THU-KEG/ADELIE/train4llama/open_instruct/gradio_demo_chat.py
pointer only (licence: NONE) · get_code("17d17a8f4a188a7d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, THU-KEG/ADELIE 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.

create_prompt_with_llama2_chat_format Ran
ran; our contract draft was wrong, not the code
THU-KEG/ADELIE/train4llama/eval/templates.py
pointer only (licence: NONE) · get_code("538471327537d426")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, THU-KEG/ADELIE 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.

create_prompt_with_olmo_chat_format Ran
ran on a synthesized input
THU-KEG/ADELIE/train4llama/eval/templates.py
pointer only (licence: NONE) · get_code("45e2cc1022c95249")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, THU-KEG/ADELIE 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.

create_prompt_with_tulu_chat_format Ran
ran; our contract draft was wrong, not the code
THU-KEG/ADELIE/train4llama/eval/templates.py
pointer only (licence: NONE); the stored copy get_code serves, from thu-keg/crab, is pointer only (licence: NONE) · get_code("697d92a5d51eff3e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, THU-KEG/ADELIE 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.

dispatch_openai_chat_requesets Ran
ran; our contract draft was wrong, not the code
THU-KEG/ADELIE/train4llama/eval/dispatch_openai_requests.py
pointer only (licence: NONE); the stored copy get_code serves, from thu-keg/crab, is pointer only (licence: NONE) · get_code("dcad9ac62979ca49")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, THU-KEG/ADELIE 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.

dispatch_openai_prompt_requesets Ran
ran; our contract draft was wrong, not the code
THU-KEG/ADELIE/train4llama/eval/dispatch_openai_requests.py
pointer only (licence: NONE); the stored copy get_code serves, from thu-keg/crab, is pointer only (licence: NONE) · get_code("71e4259026911444")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, THU-KEG/ADELIE 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.

dpo_loss Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
THU-KEG/ADELIE/train4llama/open_instruct/dpo_utils.py
pointer only (licence: NONE); the stored copy get_code serves, from luckyyysta/fine-grained-attribution, is pointer only (licence: NONE) · get_code("b2b6de249cebe189")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, THU-KEG/ADELIE 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.

encode_few_shot_example Ran
ran; our contract draft was wrong, not the code
THU-KEG/ADELIE/train4llama/open_instruct/instruction_encode_templates.py
pointer only (licence: NONE) · get_code("96351a65183bb428")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, THU-KEG/ADELIE 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.

encode_instruction_example Ran
ran; our contract draft was wrong, not the code
THU-KEG/ADELIE/train4llama/open_instruct/instruction_encode_templates.py
pointer only (licence: NONE) · get_code("f839fd4c6f96a26f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, THU-KEG/ADELIE 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.

encode_with_messages_format Ran
ran; our contract draft was wrong, not the code
THU-KEG/ADELIE/train4llama/open_instruct/finetune.py
pointer only (licence: NONE) · get_code("97229c97d4273595")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, THU-KEG/ADELIE 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.

encode_with_prompt_completion_format Ran
ran; our contract draft was wrong, not the code
THU-KEG/ADELIE/train4llama/open_instruct/finetune.py
pointer only (licence: NONE) · get_code("5966cc3120c46d61")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, THU-KEG/ADELIE 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.

generate_completions Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
THU-KEG/ADELIE/train4llama/eval/utils.py
pointer only (licence: NONE) · get_code("cdbcc01805fac313")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, THU-KEG/ADELIE 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_next_word_predictions Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
THU-KEG/ADELIE/train4llama/eval/utils.py
pointer only (licence: NONE) · get_code("d134c88af0236263")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, THU-KEG/ADELIE 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_statistics_for_messages_data Not yet run
unverified (harvested, no recorded run)
THU-KEG/ADELIE/train4llama/open_instruct/get_statistics.py
pointer only (licence: NONE) · get_code("533568a0e86ef298")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, THU-KEG/ADELIE 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_statistics_for_prompt_completion_data Not yet run
unverified (harvested, no recorded run)
THU-KEG/ADELIE/train4llama/open_instruct/get_statistics.py
pointer only (licence: NONE) · get_code("84aeb6a7586885f5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, THU-KEG/ADELIE 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.

score_completions Not yet run
unverified (harvested, no recorded run)
THU-KEG/ADELIE/train4llama/eval/utils.py
pointer only (licence: NONE); the stored copy get_code serves, from jinzhuoran/rwku, is pointer only (licence: NONE) · get_code("d029fa02758da921")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, THU-KEG/ADELIE 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 18 samples lifted from this paper's linked repositories, 18 carry a function identity and 0 do not. Of the 18 distinct functions with an identity, 18 are also present in other papers whose code we hold (16 with at least one paper dated earlier, 4 the same month, 15 later) and 0 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_next_word_predictions 10 other papers
3 dated earlier, 7 later
2401.15006 (2024-01)
Airavata: Introducing Hindi Instruction-tuned LLM
2401.16405 (2024-01)
Scaling Sparse Fine-Tuning to Large Language Models
2402.16705 (2024-02)
SelectIT: Selective Instruction Tuning for LLMs via Uncertainty-Aware Self-Reflection
and 7 more not named here
create_prompt_with_tulu_chat_format 8 other papers
3 dated earlier, 1 the same month, 4 later
2401.10768 (2024-01)
Knowledge Verification to Nip Hallucination in the Bud
2401.16405 (2024-01)
Scaling Sparse Fine-Tuning to Large Language Models
2403.03870 (2024-03)
Learning to Decode Collaboratively with Multiple Language Models
and 5 more not named here
dispatch_openai_prompt_requesets 8 other papers
5 dated earlier, 3 later
2310.06830 (2023-10)
Lemur: Harmonizing Natural Language and Code for Language Agents
2401.10768 (2024-01)
Knowledge Verification to Nip Hallucination in the Bud
2401.15006 (2024-01)
Airavata: Introducing Hindi Instruction-tuned LLM
and 5 more not named here
dispatch_openai_chat_requesets 7 other papers
5 dated earlier, 2 later
2310.06830 (2023-10)
Lemur: Harmonizing Natural Language and Code for Language Agents
2401.10768 (2024-01)
Knowledge Verification to Nip Hallucination in the Bud
2401.15006 (2024-01)
Airavata: Introducing Hindi Instruction-tuned LLM
and 4 more not named here
dpo_loss 6 other papers
3 dated earlier, 3 later
2305.14718 (2023-05)
Leftover Lunch: Advantage-based Offline Reinforcement Learning for Language Models
2309.16240 (2023-09)
Beyond Reverse KL: Generalizing Direct Preference Optimization with Diverse Divergence Constraints
2312.00267 (2023-12)
Sample Efficient Preference Alignment in LLMs via Active Exploration
and 3 more not named here
score_completions 6 other papers
1 dated earlier, 5 later
2402.16705 (2024-02)
SelectIT: Selective Instruction Tuning for LLMs via Uncertainty-Aware Self-Reflection
2406.10890 (2024-06)
RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Models
2410.24175 (2024-10)
Constraint Back-translation Improves Complex Instruction Following of Large Language Models
and 3 more not named here
generate_completions 5 other papers
1 dated earlier, 4 later
2402.16705 (2024-02)
SelectIT: Selective Instruction Tuning for LLMs via Uncertainty-Aware Self-Reflection
2410.24175 (2024-10)
Constraint Back-translation Improves Complex Instruction Following of Large Language Models
2504.11393 (2025-04)
How to Predict Best Pretraining Data with Small Experiments
and 2 more not named here
encode_with_prompt_completion_format 4 other papers
1 dated earlier, 1 the same month, 2 later
2402.16705 (2024-02)
SelectIT: Selective Instruction Tuning for LLMs via Uncertainty-Aware Self-Reflection
2405.20974 (2024-05)
SaySelf: Teaching LLMs to Express Confidence with Self-Reflective Rationales
2406.15444 (2024-06)
Published at ICLR 2025 Workshop on Reasoning and Planning for LLMs CUTTING THROUGH THE NOISE: BOOSTING LLM PERFORMANCE ON MATH WORD PROBLEMS
and 1 more not named here
encode_few_shot_example 3 other papers
1 dated earlier, 1 the same month, 1 later
2312.07540 (2023-12)
diff History for Neural Language Agents
2405.14394 (2024-05)
Instruction Tuning With Loss Over Instructions
2410.16208 (2024-10)
Compute-Constrained Data Selection
encode_instruction_example 3 other papers
1 dated earlier, 1 the same month, 1 later
2312.07540 (2023-12)
diff History for Neural Language Agents
2405.14394 (2024-05)
Instruction Tuning With Loss Over Instructions
2410.16208 (2024-10)
Compute-Constrained Data Selection
encode_with_messages_format 3 other papers
1 dated earlier, 2 later
2402.16705 (2024-02)
SelectIT: Selective Instruction Tuning for LLMs via Uncertainty-Aware Self-Reflection
2406.15444 (2024-06)
Published at ICLR 2025 Workshop on Reasoning and Planning for LLMs CUTTING THROUGH THE NOISE: BOOSTING LLM PERFORMANCE ON MATH WORD PROBLEMS
2410.16208 (2024-10)
Compute-Constrained Data Selection
concatenated_forward 2 other papers
2 later
2408.04568 (2024-08)
Learning Fine-Grained Grounded Citations for Attributed Large Language Models
2410.16208 (2024-10)
Compute-Constrained Data Selection
concatenated_inputs 2 other papers
2 later
2408.04568 (2024-08)
Learning Fine-Grained Grounded Citations for Attributed Large Language Models
2410.16208 (2024-10)
Compute-Constrained Data Selection
create_prompt_with_llama2_chat_format 2 other papers
1 dated earlier, 1 later
2402.16705 (2024-02)
SelectIT: Selective Instruction Tuning for LLMs via Uncertainty-Aware Self-Reflection
2505.07437 (2025-05)
LEAD: Iterative Data Selection for Efficient LLM Instruction Tuning
create_prompt_with_olmo_chat_format 2 other papers
1 dated earlier, 1 later
2402.16705 (2024-02)
SelectIT: Selective Instruction Tuning for LLMs via Uncertainty-Aware Self-Reflection
2505.07437 (2025-05)
LEAD: Iterative Data Selection for Efficient LLM Instruction Tuning
convert_message 1 other paper
1 dated earlier
2401.15006 (2024-01)
Airavata: Introducing Hindi Instruction-tuned LLM
get_statistics_for_messages_data 1 other paper
1 dated earlier
2401.15006 (2024-01)
Airavata: Introducing Hindi Instruction-tuned LLM
get_statistics_for_prompt_completion_data 1 other paper
1 dated earlier
2401.15006 (2024-01)
Airavata: Introducing Hindi Instruction-tuned LLM

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) usually fall short on information extraction (IE) tasks and struggle to follow the complex instructions of IE tasks. This primarily arises from LLMs not being aligned with humans, as mainstream alignment datasets typically do not include IE data. In this paper, we introduce ADELIE (Aligning large language moDELs on Information Extraction), an aligned LLM that effectively solves various IE tasks, including closed IE, open IE, and on-demand IE. We first collect and construct a high-quality alignment corpus IEInstruct for IE. Then we train ADELIE SFT using instruction tuning on IEInstruct. We further train ADELIE SFT with direct preference optimization (DPO) objective, resulting in ADELIE DPO . Extensive experiments on various held-out IE datasets demonstrate that our models (ADELIE SFT and ADELIE DPO ) achieve state-of-the-art (SoTA) performance among open-source models. We further explore the general capabilities of ADELIE, and experimental results reveal that their general capabilities do not exhibit a noticeable decline. We have released the code, data, and models to facilitate further research. 1

For agents

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

get_harvested_code_for_paper("2405.05008")
get_code_for_paper("2405.05008")
have("2405.05008")

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

curl https://syntology.ai/api/ran/2405.05008.json

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

[![Syntology run record](https://syntology.ai/api/ran/2405.05008.svg)](https://syntology.ai/paper/2405.05008)

Connect an agent — have() is free.