Papers › Never Lost in the Middle: Mastering Long-Context Question Answering with...

Never Lost in the Middle: Mastering Long-Context Question Answering with Position-Agnostic Decompositional Training

15 Nov 2023arXiv:2311.09198archive 2025-07-28

Junqing He, Kunhao Pan, Xiaoqun Dong, Zhuoyang Song, Yibo Liu, Qianguo Sun, Yuxin Liang, Hao Wang, Enming Zhang, Jiaxing Zhang

While large language models (LLMs) are equipped with longer text input capabilities than before, they are struggling to seek correct information in long contexts. The "lost in the middle" problem challenges most LLMs, referring to the dramatic decline in accuracy when correct information is located in the middle. To overcome this crucial issue, this paper proposes to enhance the information searching and reflection ability of LLMs in long contexts via specially designed tasks called Attention Strengthening Multi-doc QA (ASM QA). Following these tasks, our model excels in focusing more precisely on the desired information. Experimental results show substantial improvement in Multi-doc QA and other benchmarks, superior to state-of-the-art models by 13.7% absolute gain in shuffled settings, by 21.5% in passage retrieval task. We release our model, Ziya-Reader to promote related research in the community.

PaperPDFCodeCode Syntology ran

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 17 code samples harvested from 2 repositories linked to this paper: 15 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 1 violated, 10 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 15 samples from 1 repository, 14 ran (12 with no instrument failure; 2 where Syntology's instrument failed); community (archive-listed): 2 samples from 1 repository, 1 ran (0 with no instrument failure; 1 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 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 3 of the 15 samples that ran have no recorded date.

hejunqing/never-lost-in-the-middle officialmentioned in papermentioned on GitHubpytorchMITSyntology: 15 samples, 14 ran (2 instrument-failed) · 1 unverified report
qihoo360/360zhinao mentioned on GitHubpytorchApache-2.0Syntology: 2 samples, 1 ran (1 instrument-failed) · 1 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

17 samples harvested: 15 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 1 violated, 10 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
1ran · violated contract
3ran · our draft was wrong
10ran
2unverified

Licence: 3 of the 17 samples are pointer only, meaning Syntology does not serve that copy's text. For 3 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

hejunqing/never-lost-in-the-middle official repository 15 samples, 14 ran (2 instrument-failed) · 1 unverified
add_eod LongBench/src/new_utils.py ran fingerprinted MIT (permissive) · afdae69731929a72 · report fixture: signature input_text:str/0/str, dataset:str/0/str · returned str · level recorded 2026-09-24
build_chat in 29 papers Lost_Retrieval/src/pred_single.py ran MIT (permissive) · 251720ea85d2ca71 · report fixture: signature tokenizer:MockTokenizer/0/?, tokenized_prompt:list/1/int, prompt:str/0/str · returned str · level recorded 2026-09-24
build_chat in 29 papers LongBench/src/baichuan_pred_shuffle.py ran MIT (permissive) · 7024e12377186e51 · report fixture: signature tokenizer:MockTokenizer/0/?, tokenized_prompt:list/1/int, prompt:str/0/str · returned str · level recorded 2026-09-24
build_chat in 29 papers LongBench/src/pred_chatglm.py ran MIT (permissive) · 7439724189daf2cb · report fixture: signature tokenizer:ChatGLM3Tokenizer/0/?, prompt:str/0/str, model_name:str/0/str · returned str · level recorded 2026-09-24
build_chat2 Lost_Retrieval/src/pred_single.py ran MIT (permissive) · 619fcfb88a0948e5 · report fixture: signature tokenizer:MockTokenizer/0/?, tokenized_prompt:list/1/int, prompt:str/0/str · returned str · level recorded 2026-09-24
build_chat_baichuan LongBench/src/pred_shuffle_reader.py ran MIT (permissive) · 9cea8a9dc64a79cc · report fixture: signature tokenizer:DummyTokenizer/0/?, tokenized_prompt:Tensor/2/int, prompt:str/0/str · returned str · level recorded 2026-09-24
count_score in 27 papers LongBench/src/metrics.py ran · honoured contract fingerprinted MIT (permissive) here; the stored copy is pointer only · b349b79d9cc2934b · report fixture: signature prediction:str/0/str, ground_truth:int/0/int · returned float · level recorded, date not recorded
get_pred in 20 papers LongBench/src/baichuan_pred_shuffle.py ran MIT (permissive) · 9ac0485160d687f7 · report fixture: signature model:callable/0/?, tokenizer:callable/0/?, data:list/1/dict, max_length:int/0/int, max_gen:int/0/int, prompt_format:str/0/str, dataset:str/0/str, device:str/0/str · returned list · level recorded 2026-09-24
normalize_answer in 304 papers LongBench/src/metrics.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · e7e75981cb464788 · report fixture: signature s:str/0/str · returned str · level recorded, date not recorded
normalize_zh_answer in 32 papers LongBench/src/metrics.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · 8c5c581f9264c810 · report fixture: signature s:str/0/str · returned str · level recorded, date not recorded
parse_args in 355 papers LongBench/src/pred_chatglm.py ran MIT (permissive) · 36753478d8bfe1e1 · report fixture: signature args:list/1/str · returned Namespace · level recorded 2026-09-24
post_process in 56 papers LongBench/src/pred_chatglm.py ran · violated contract fingerprinted MIT (permissive) · 4489113b536ca6eb · report fixture: signature response:str/0/str, model_name:str/0/str · returned str · level recorded 2026-09-22
replace_head LongBench/src/new_utils.py ran MIT (permissive) · 372ffbf8201660a5 · report fixture: signature context:str/0/str, dataset:str/0/str · returned str · level recorded 2026-09-24
shorten in 5 papers LongBench/src/new_utils.py ran fingerprinted MIT (permissive) · 6653c42aad855a65 · report fixture: signature context:str/0/str, sep:str/0/str, num:int/0/int · returned str · level recorded 2026-09-24
build_chat in 29 papers LongBench/src/pred_shuffle_reader.py unverified MIT (permissive) · 0af745ab8b003692 · report
qihoo360/360zhinao community (archive-listed) 2 samples, 1 ran (1 instrument-failed) · 1 unverified
preprocess in 284 papers
census: 11 implementations from 13 papers, 10 distinct outputs across 5 buckets, one shared input per bucket
Reranking/finetune.py ran · our draft was wrong Apache-2.0 (permissive) · 8b733c9fc590e4c1 · report fixture: signature sources:list/1/list, tokenizer:callable/0/?, max_len:int/0/int, system_message:str/0/str · returned dict · level recorded 2026-09-22

Tasks

Passage RetrievalQuestion AnsweringRetrieval

1 archive task tag without a task page not shown.

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