Paper Detail

Evaluation of Contextual Understanding in Large Language Models

Subavarshana Arumugam, Mamta Nallaretnam, Kithuni Wickramasinghe, Chamath Gunapala, Pragatheeswaran Vipulanandan, Uthayasanker Thayasivam, Kamal Premaratne

arxiv Score 16.2

Published 2026-09-08 · First seen 2026-09-09

General AI

Abstract

Large Language Models (LLMs) demonstrate impressive performance across diverse NLP tasks, yet their ability to exhibit genuine contextual understanding remains uncertain. Traditional evaluation metrics such as perplexity, BiLingual Evaluation Understudy (BLEU), or surface-level accuracy fail to reveal how well LLMs extract, integrate, and reason over contextual information--a gap particularly critical in question answering, where models must align responses with contextually grounded knowledge rather than memorized associations. We propose a novel knowledge graph-based evaluation framework introducing Semantic Structural Similarity for KGs (S3KG), a hybrid similarity measure integrating structural and semantic similarity into a continuous evaluation score, alongside a diagnostic framework for categorizing reasoning errors. To validate this pipeline, we evaluate S3KG against established metrics on a curated question-answer (QA) benchmark, demonstrating its effectiveness in measuring correctness, faithfulness, and interpretability in LLM-generated responses.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
now
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@article{arumugam2026evaluation,
  title = {Evaluation of Contextual Understanding in Large Language Models},
  author = {Subavarshana Arumugam and Mamta Nallaretnam and Kithuni Wickramasinghe and Chamath Gunapala and Pragatheeswaran Vipulanandan and Uthayasanker Thayasivam and Kamal Premaratne},
  year = {2026},
  abstract = {Large Language Models (LLMs) demonstrate impressive performance across diverse NLP tasks, yet their ability to exhibit genuine contextual understanding remains uncertain. Traditional evaluation metrics such as perplexity, BiLingual Evaluation Understudy (BLEU), or surface-level accuracy fail to reveal how well LLMs extract, integrate, and reason over contextual information--a gap particularly critical in question answering, where models must align responses with contextually grounded knowledge r},
  url = {https://arxiv.org/abs/2609.09004},
  keywords = {cs.CL, cs.LG},
  eprint = {2609.09004},
  archiveprefix = {arXiv},
}

Metadata

{}