Skip to content
AI News HubLIVE
Original source2 min read

Tracing Knowledge and Reasoning in LLM

Summary

A TACL-accepted paper by Yang Wang and six co-authors proposes a task-centric framework that characterizes the model-internal processing elicited by benchmarks using attention-, activation-, and representation-based signals. Evaluating 16 LLMs across 24 benchmarks, it finds systematic processing differences between knowledge-centric and reasoning-centric tasks.

SourcearXiv Computational LinguisticsAuthor: Yang Wang, Xiao Wang, Yiqi Liu, Chenghao Xiao, Eleni Vasilaki, Goran Nenadic, Chenghua Lin
Tracing Knowledge and Reasoning in LLM
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 12 Nov 2026]

Title:Tracing Knowledge and Reasoning in LLM

View a PDF of the paper titled Tracing Knowledge and Reasoning in LLM, by Yang Wang and 6 other authors

View PDF HTML (experimental)

Abstract:Current evaluations of Large Language Models (LLMs) report performance at the dataset or task level, revealing what a model achieves but offering little insight into the internal processing associated with its performance. We propose a task-centric framework for characterising the model-internal processing elicited by a benchmark. It combines attention- and activation-based signals with representation-based measures to characterise benchmarks spanning a continuum from retrieval-dominant to reasoning-dominant and to surface failure modes that task-level scores conceal. We evaluate 16 LLMs across 24 diverse benchmarks and conduct targeted internal-state analyses on representative models and tasks, observing systematic differences in processing between knowledge-centric and reasoning-centric tasks. We shift evaluation from asking what score a model achieves toward characterising the processing patterns associated with that score, potentially supporting more targeted benchmark selection and more informed model choice. We open source our code at this https URL.

Comments: This paper was accepted with an A-decision to Transactions of the Association for Computational Linguistics. This version is the pre-publication version prior to MIT Press production

Subjects:

Computation and Language (cs.CL)

Cite as: arXiv:2611.17461 [cs.CL]

(or arXiv:2611.17461v1 [cs.CL] for this version)

https://doi.org/10.48550/arXiv.2611.17461

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Yang Wang [view email] [v1] Thu, 12 Nov 2026 19:39:00 UTC (258 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Tracing Knowledge and Reasoning in LLM, by Yang Wang and 6 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

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

InvestorsAdvanced

Key points

  • Proposes a task-centric framework combining attention-based, activation-based, and representation-based measures to characterize benchmarks.
  • Evaluates 16 LLMs across 24 benchmarks spanning a continuum from retrieval-dominant to reasoning-dominant tasks.
  • Surfaces failure modes hidden by task-level scores and distinguishes knowledge-centric from reasoning-centric processing.
  • Accepted with an A-decision to Transactions of the Association for Computational Linguistics; code is open sourced.

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