Papers › Dynamic Chunking and Selection for Reading Comprehension of Ultra-Long Context in...

Dynamic Chunking and Selection for Reading Comprehension of Ultra-Long Context in Large Language Models

1 Jun 2025arXiv:2506.00773archive 2025-07-28

Boheng Sheng, Jiacheng Yao, Meicong Zhang, Guoxiu He

Large language models (LLMs) often struggle to accurately read and comprehend extremely long texts. Current methods for improvement typically rely on splitting long contexts into fixed-length chunks. However, fixed truncation risks separating semantically relevant content, leading to ambiguity and compromising accurate understanding. To overcome this limitation, we propose a straightforward approach for dynamically separating and selecting chunks of long context, facilitating a more streamlined input for LLMs. In particular, we compute semantic similarities between adjacent sentences, using lower similarities to adaptively divide long contexts into variable-length chunks. We further train a question-aware classifier to select sensitive chunks that are critical for answering specific questions. Experimental results on both single-hop and multi-hop question-answering benchmarks show that the proposed approach consistently outperforms strong baselines. Notably, it maintains robustness across a wide range of input lengths, handling sequences of up to 256k tokens. Our datasets and code are available at the following link: https://github.com/ECNU-Text-Computing/DCS

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 9 code samples harvested from 1 repository linked to this paper: 9 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 8 where Syntology's instrument failed) · 0 unverified. Where Syntology's instrument failed: 6 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 9 samples from 1 repository, 9 ran (1 with no instrument failure; 8 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.

ecnu-text-computing/dcs officialmentioned in paperpytorchSyntology: 9 samples, 9 ran (8 instrument-failed) · 0 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

9 samples harvested: 9 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 8 where Syntology's instrument failed) · 0 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 · violated contract
6ran · our draft was wrong
2ran; the contract check could not run

Licence: 9 of the 9 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 ecnu-text-computing/dcs. “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.

ecnu-text-computing/dcs official repository 9 samples, 9 ran (8 instrument-failed) · 0 unverified
calculate_cosine_distances sentence_chunk.py ran · our draft was wrong no licence file found · pointer only · ac05385d5416a956 · report fixture: signature sentences:list/1/dict · returned tuple · level recorded 2026-09-22
chunk_com sentence_chunk.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · fab419bb269242a4 · report fixture: signature distances:ndarray/1/float, bpp_threshold:int/0/int · returned tuple · level recorded 2026-09-22
chunk_gen sentence_chunk.py ran · our draft was wrong no licence file found · pointer only · 98d6f09b0f94434e · report fixture: signature indices_above_thresh:list/1/int, sentences:list/1/dict · returned tuple · level recorded 2026-09-24
chunk_re_gen sentence_chunk.py ran; the contract check could not run (RAISES) no licence file found · pointer only · 342a38431851494e · report fixture: signature chunks:list/1/str, chunks_len:list/1/int, max_chunk_len:int/0/int · returned tuple · level recorded 2026-09-22
combine_sentences sentence_chunk.py ran · our draft was wrong no licence file found · pointer only · 05174a27a000c05a · report fixture: signature sentences:list/1/dict, buffer_size:int/0/int · returned list · level recorded 2026-09-22
cosine_similarity in 120 papers
census: 26 implementations from 30 papers, 11 distinct outputs across 5 buckets, one shared input per bucket this sample: bucket 2 of 5, arg 1: rank 1, kind float, dtype float64 · arg 2: rank 1, kind float, dtype float64
sentence_chunk.py ran · violated contract fingerprinted no licence file found · pointer only · 91467442d43e757d · report fixture: signature vec1:ndarray/1/float, vec2:ndarray/1/float · returned float64 · level recorded 2026-09-22
sentence_chunking sentence_chunk.py ran · our draft was wrong no licence file found · pointer only · dd97bd6d8181e354 · report fixture: signature model:MockModel/0/?, text:str/0/str, bpp_threshold:int/0/int · returned tuple · level recorded 2026-09-24
sentence_chunking_main sentence_chunk.py ran · our draft was wrong no licence file found · pointer only · 83212d1183d655a4 · report fixture: signature chunk_len:int/0/int, bpp_threshold:int/0/int, re_combine:bool/0/bool, text:str/0/str, model:callable/0/? · returned tuple · level recorded 2026-09-22
sentence_split sentence_chunk.py ran · our draft was wrong fingerprinted no licence file found · pointer only · ec3b031cb417d57c · report fixture: signature text:str/0/str · returned list · level recorded 2026-09-22

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 Dynamic Chunking and Selection (graph method: Dynamic Chunking and Selection). 9 bricks; individually on a fixture: 9 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 8 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

  1. sentence_chunking_main entry · level 1 · ran · our draft was wrong · 83212d1183d655a4
  2. chunk_re_gen helper · level 1 · ran; the contract check could not run (RAISES) · 342a38431851494e
  3. sentence_chunking data_transform · level 1 · ran · our draft was wrong · dd97bd6d8181e354
  4. calculate_cosine_distances metric · level 1 · ran · our draft was wrong · ac05385d5416a956
  5. chunk_com helper · level 1 · ran; the contract check could not run (RAISES) · fab419bb269242a4
  6. chunk_gen helper · level 1 · ran · our draft was wrong · 98d6f09b0f94434e
  7. combine_sentences data_transform · level 1 · ran · our draft was wrong · 05174a27a000c05a
  8. sentence_split data_transform · level 1 · ran · our draft was wrong · ec3b031cb417d57c
  9. cosine_similarity metric · level 1 · ran · violated contract · 91467442d43e757d

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="2506.00773") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

ChunkingMulti-hop Question AnsweringQuestion AnsweringReading Comprehension

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