Papers › CItruS: Chunked Instruction-aware State Eviction for Long Sequence Modeling

CItruS: Chunked Instruction-aware State Eviction for Long Sequence Modeling

17 Jun 2024arXiv:2406.12018archive 2025-07-28

Yu Bai, Xiyuan Zou, Heyan Huang, Sanxing Chen, Marc-Antoine Rondeau, Yang Gao, Jackie Chi Kit Cheung

Long sequence modeling has gained broad interest as large language models (LLMs) continue to advance. Recent research has identified that a large portion of hidden states within the key-value caches of Transformer models can be discarded (also termed evicted) without affecting the perplexity performance in generating long sequences. However, we show that these methods, despite preserving perplexity performance, often drop information that is important for solving downstream tasks, a problem which we call information neglect. To address this issue, we introduce Chunked Instruction-aware State Eviction (CItruS), a novel modeling technique that integrates the attention preferences useful for a downstream task into the eviction process of hidden states. In addition, we design a method for chunked sequence processing to further improve efficiency. Our training-free method exhibits superior performance on long sequence comprehension and retrieval tasks over several strong baselines under the same memory budget, while preserving language modeling perplexity. The code and data have been released at https://github.com/ybai-nlp/CItruS.

PaperPDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2406.12018")

Code

Syntology Ran 5 of 10 code samples harvested from 1 repository linked to this paper; 5 have no recorded run. Of those that ran: 5 ran · fixture could not drive it.

By repository: official repository: 10 samples from 1 repository, 5 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

ybai-nlp/CItruS officialmentioned in papermentioned on GitHubpytorch 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

10 samples harvested; 5 ran; 0 honoured the contract we drafted; 5 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

5ran · fixture could not drive it
5unverified

Licence: 10 of the 10 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 ybai-nlp/CItruS. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

apply_rotary_pos_emb_single ybai-nlp/CItruS/src/citrus_methods.py official repository ran · fixture could not drive it no licence file found · pointer only · feb1b3f32d2a6b1d · report
get_past_key_values_instruction_aware_single ybai-nlp/CItruS/src/citrus_methods.py official repository ran · fixture could not drive it no licence file found · pointer only · bcbb23a09017e873 · report
get_past_key_values_standard ybai-nlp/CItruS/src/citrus_methods.py official repository ran · fixture could not drive it no licence file found · pointer only · 536f4a58379b992a · report
get_past_key_values_with_instruction_aware_double ybai-nlp/CItruS/src/citrus_methods.py official repository ran · fixture could not drive it no licence file found · pointer only · 99816d85ee9c97a0 · report
llama_pos_shift_attention_forward ybai-nlp/CItruS/src/citrus_methods.py official repository ran · fixture could not drive it no licence file found · pointer only · fba04c2f8cfb0944 · report
decoding ybai-nlp/CItruS/src/citrus_methods.py official repository unverified no licence file found · pointer only · 56f48a4c656eed1b · report
enable_llama_pos_shift_attention ybai-nlp/CItruS/src/citrus_methods.py official repository unverified no licence file found · pointer only · 54e3e8b62733f14d · report
enable_mistral_pos_shift_attention ybai-nlp/CItruS/src/citrus_methods.py official repository unverified no licence file found · pointer only · ada54363a9f4af14 · report
generate_with_citrus ybai-nlp/CItruS/src/citrus_methods.py official repository unverified no licence file found · pointer only · 401a35fa33f1eb57 · report
mistral_pos_shift_attention_forward ybai-nlp/CItruS/src/citrus_methods.py official repository unverified no licence file found · pointer only · d1c34504b6b5a6a8 · report

Tasks

Language ModelingLanguage ModellingRetrieval

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

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