Papers › Instruction Tuning With Loss Over Instructions

Instruction Tuning With Loss Over Instructions

23 May 2024arXiv:2405.14394archive 2025-07-28

Zhengyan Shi, Adam X. Yang, Bin Wu, Laurence Aitchison, Emine Yilmaz, Aldo Lipani

Instruction tuning plays a crucial role in shaping the outputs of language models (LMs) to desired styles. In this work, we propose a simple yet effective method, Instruction Modelling (IM), which trains LMs by applying a loss function to the instruction and prompt part rather than solely to the output part. Through experiments across 21 diverse benchmarks, we show that, in many scenarios, IM can effectively improve the LM performance on both NLP tasks (e.g., MMLU, TruthfulQA, and HumanEval) and open-ended generation benchmarks (e.g., MT-Bench and AlpacaEval). Remarkably, in the most advantageous case, IM boosts model performance on AlpacaEval 1.0 by over 100%. We identify two key factors influencing the effectiveness of IM: (1) The ratio between instruction length and output length in the training data; and (2) The number of training examples. We observe that IM is especially beneficial when trained on datasets with lengthy instructions paired with brief outputs, or under the Superficial Alignment Hypothesis (SAH) where a small amount of training examples are used for instruction tuning. Further analysis substantiates our hypothesis that our improvement can be attributed to reduced overfitting to instruction tuning datasets. It is worth noting that we are not proposing \ours as a replacement for current fine-tuning processes. Instead, our work aims to provide practical guidance for instruction tuning LMs, especially in low-resource scenarios.

PaperPDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 20 code samples harvested from 1 repository linked to this paper: 16 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 1 violated, 10 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 20 samples from 1 repository, 16 ran (11 with no instrument failure; 5 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

zhengxiangshi/instructionmodelling officialmentioned in papermentioned on GitHubpytorchSyntology: 20 samples, 16 ran (5 instrument-failed) · 4 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

20 samples harvested: 16 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 1 violated, 10 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · violated contract
4ran · our draft was wrong
1ran; the contract check could not run
10ran
4unverified

Licence: 20 of the 20 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from zhengxiangshi/instructionmodelling. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

zhengxiangshi/instructionmodelling official repository 20 samples, 16 ran (5 instrument-failed) · 4 unverified
add_ref_model_logit_to_columns src/finetune_kl.py ran; the contract check could not run (RAISES) no licence file found · pointer only · 1447821f32348ac5 · report fixture: signature example:dict/0/?, ref_model_logit:Tensor/2/float · returned dict · level recorded 2026-09-24
compute_kl_divergence_loss src/utils.py ran no licence file found · pointer only · 9104e80d99f2ab8a · report fixture: signature output_logits:Tensor/3/float, ref_logits:Tensor/3/float, input_ids:Tensor/2/int, labels:Tensor/2/int, kl_penalty:str/0/str · returned Tensor · level recorded 2026-09-24
compute_llm_eval_performance src/get_results_group.py ran no licence file found · pointer only · 969b779909d41a48 · report fixture: signature path:str/0/str, model_name:str/0/str · returned tuple · level recorded 2026-09-24
create_prompt_with_tulu_chat_format in 13 papers src/generate.py ran no licence file found · pointer only · 697d92a5d51eff3e · report fixture: signature messages:list/1/dict, bos:str/0/str, eos:str/0/str, add_bos:bool/0/bool · returned str · level recorded 2026-09-25
encode_few_shot_example src/instruction_encode_templates.py ran no licence file found · pointer only · 96351a65183bb428 · report fixture: signature instruction:str/0/str, examplars:list/1/dict, input:str/0/str, output:str/0/str, eos_token:str/0/str · returned dict · level recorded 2026-09-26
encode_instruction_example in 5 papers src/instruction_encode_templates.py ran no licence file found · pointer only · f839fd4c6f96a26f · report fixture: signature instruction:str/0/str, input:str/0/str, output:str/0/str, random_template:bool/0/bool, eos_token:str/0/str · returned dict · level recorded 2026-09-26
encode_with_messages_format in 21 papers src/compute_loss.py ran · our draft was wrong no licence file found · pointer only · 1cb0eeb16cf04ee3 · report fixture: signature example:dict/0/?, tokenizer:callable/0/?, max_seq_length:int/0/int · returned dict · level recorded 2026-09-22
encode_with_messages_format in 21 papers src/finetune.py ran no licence file found · pointer only · 8a32cc283c5e5807 · report fixture: signature example:dict/0/?, tokenizer:callable/0/?, max_seq_length:int/0/int, use_lm_loss:bool/0/bool · returned dict · level recorded 2026-09-24
encode_with_messages_format in 21 papers src/finetune_kl.py ran no licence file found · pointer only · fc23892a28f95bc1 · report fixture: signature example:dict/0/?, tokenizer:callable/0/?, max_seq_length:int/0/int, use_lm_loss:bool/0/bool · returned dict · level recorded 2026-09-24
encode_with_prompt_completion_format in 25 papers src/compute_loss.py ran · our draft was wrong no licence file found · pointer only · c90f3a5ec6457c6d · report fixture: signature example:dict/0/?, tokenizer:callable/0/?, max_seq_length:int/0/int · returned dict · level recorded 2026-09-22
encode_with_prompt_completion_format in 25 papers src/finetune.py ran no licence file found · pointer only · e7170ef85d1fec78 · report fixture: returned dict · level recorded 2026-09-24
get_human_eval_results src/get_results_group.py ran no licence file found · pointer only · cb1ba0cfe1a9de8a · report fixture: signature humaneval_path:str/0/str, model_name:str/0/str, metric_name:str/0/str · returned float · level recorded 2026-09-24
get_instruction in 10 papers src/generate.py ran · our draft was wrong no licence file found · pointer only · 88c99652268092f3 · report fixture: signature example:dict/0/? · returned str · level recorded 2026-09-24
group_texts in 14 papers src/compute_loss.py ran · our draft was wrong no licence file found · pointer only · d09e0781a55d3694 · report fixture: signature examples:dict/0/?, block_size:int/0/int · returned dict · level recorded 2026-09-24
neftune_post_forward_hook src/utils.py ran no licence file found · pointer only · 8813cfd84beec509 · report fixture: returned Tensor · level recorded 2026-09-24
should_be_filtered src/reformat_datasets.py ran · violated contract no licence file found · pointer only · 08f4816632095bc7 · report fixture: signature example:dict/0/? · returned bool · level recorded 2026-09-26
compute_kl_divergence_loss_target_token src/utils.py unverified no licence file found · pointer only · c46f87d3e93c4108 · report
compute_model_performance src/get_results_group.py unverified no licence file found · pointer only · 9cc81ad65b572087 · report
main in 235 papers src/compute_loss.py unverified no licence file found · pointer only · e5ce78b681258794 · report
parse_args in 355 papers src/compute_loss.py unverified no licence file found · pointer only · 1c89153db0460637 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for INSTRUCTION MODELLING (IM) (graph method: INSTRUCTION MODELLING (IM)). 4 bricks; individually on a fixture: 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

  1. main entry · level 0 · unverified · e5ce78b681258794
  2. encode_with_messages_format data_transform · level 1 · ran · our draft was wrong · 1cb0eeb16cf04ee3
  3. encode_with_prompt_completion_format data_transform · level 1 · ran · our draft was wrong · c90f3a5ec6457c6d
  4. parse_args helper · level 0 · unverified · 1c89153db0460637

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2405.14394") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

HumanEvalMMLUTruthfulQA

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections