Skip to content
AI News HubLIVE
Original source2 min read

SELD: Detecting Silent Evidence Loss in Context Compression beyond the Answer

Summary

SELD is a training-free and label-free method that detects silent evidence loss in context compression by comparing a reader model's preferences over unspoken answers before and after compression, achieving 83% identification rate on a benchmark.

SourcearXiv Computational LinguisticsAuthor: Wentao Lei, Li Liu
SELD: Detecting Silent Evidence Loss in Context Compression beyond the Answer
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 14 Oct 2026]

Title:SELD: Detecting Silent Evidence Loss in Context Compression beyond the Answer

View a PDF of the paper titled SELD: Detecting Silent Evidence Loss in Context Compression beyond the Answer, by Wentao Lei and 1 other authors

View PDF HTML (experimental)

Abstract:Context compression is now routine for language models with long inputs, but a compressed context is useful only if it keeps the evidence for the answer. Existing checks compare the reader model's answer or its most likely words, and thus miss a frequent failure, silent evidence loss: key evidence is removed while the answer stays the same, leaving the answer unsupported and risky for other models that reuse the context. To address this challenge, we propose SELD (Silent Evidence Loss Detector), which needs no training and no labels. Its principle is that when evidence is lost, a reader model's preferences among the answers it leaves unsaid shift even if its answer does not, so comparing these preferences before and after compression reveals losses that answer checks cannot see. We also build SEL-Pairs, a benchmark of length-matched evidence and control deletions from three question-answering datasets. Quantitative and qualitative experiments with five reader models on it show that SELD consistently outperforms strong and recent baselines across compressors, compression rates and models, identifying the evidence-removing edit in 83% of matched pairs with unchanged answers, against 70% for the strongest baseline. These results show that evidence loss in compressed contexts can be detected even when the answer is unchanged.

Subjects:

Computation and Language (cs.CL); Artificial Intelligence (cs.AI)

Cite as: arXiv:2611.12903 [cs.CL]

(or arXiv:2611.12903v1 [cs.CL] for this version)

https://doi.org/10.48550/arXiv.2611.12903

arXiv-issued DOI via DataCite

Submission history

From: Wentao Lei [view email] [v1] Wed, 14 Oct 2026 15:58:07 UTC (535 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled SELD: Detecting Silent Evidence Loss in Context Compression beyond the Answer, by Wentao Lei and 1 other authors

View PDF

HTML (experimental)

TeX Source

view license

Additional Features

Audio Summary

Current browse context:

cs.CL

new | recent | 2026-11

Change to browse by:

cs cs.AI

References & Citations

SciX

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • Silent evidence loss occurs when compression removes key evidence but leaves the answer unchanged, which existing answer-based checks miss.
  • SELD detects evidence loss by comparing shifts in model preferences among unspoken answers, requiring no training or labels.
  • SEL-Pairs benchmark provides length-matched evidence and control deletions from three QA datasets.
  • SELD identifies evidence-removing edits in 83% of matched pairs with unchanged answers, outperforming the strongest baseline (70%).

Highlights and analysis are generated automatically and may contain errors. Check the original source.