Challenge: Existing benchmarks for deep text understanding have encountered two major limitations . most require human annotation of knowledge, which leads to limited knowledge coverage .
Approach: They propose a benchmark to help readers understand a document with prior knowledge . they use massive knowledge bases to guide annotators and large language models to construct knowledgable questions .
Outcome: The proposed benchmarks have limited knowledge coverage and use choices or spans as answers, which results in narrow answer space.

Similar Papers

Beyond Facts- Benchmarking Distributional Reading Comprehension in Large Language Models (2026.findings-acl)

Copied to clipboard

Challenge: Existing reading comprehension benchmarks focus on factual information, but many real-world tasks require distributional knowledge expressed across text.
Approach: They propose a reading comprehension benchmark for LLMs to evaluate their ability to infer distributional knowledge from natural language.
Outcome: Experiments with multiple LLMs show that the model outperforms baselines, but performance varies widely across distribution types and characteristics.
DuoRC: Towards Complex Language Understanding with Paraphrased Reading Comprehension (P18-1)

Copied to clipboard

Challenge: DuoRC contains 186,089 unique question-answer pairs created from 7680 movie plots .
Approach: They propose a novel dataset for Reading Comprehension that motivates new challenges for neural approaches in language understanding beyond those offered by existing RC datasets.
Outcome: The proposed dataset motivates several new challenges for neural approaches in language understanding beyond those offered by existing RC datasets.
IIRC: A Dataset of Incomplete Information Reading Comprehension Questions (2020.emnlp-main)

Copied to clipboard

Challenge: Existing reading comprehension tasks focus on questions for which the contexts provide all the information required to answer them, thus not evaluating a system’s performance at identifying a potential lack of sufficient information and locating sources for that information.
Approach: They propose to use a dataset with 13K questions over paragraphs from English Wikipedia that provide only partial information to answer them, with the missing information occurring in one or more linked documents.
Outcome: The proposed model achieves 31.1% F1 on the reading comprehension task, while estimated human performance is 88.4%.
GraCoRe: Benchmarking Graph Comprehension and Complex Reasoning in Large Language Models (2025.coling-main)

Copied to clipboard

Challenge: Existing benchmarks focus primarily on pure graph understanding, lacking a comprehensive evaluation across all graph types and detailed capability definitions.
Approach: They propose a benchmark to evaluate LLMs' graph comprehension and reasoning abilities using a three-tier hierarchical taxonomy and a granular taxonomies.
Outcome: The proposed model includes 11 datasets with 5,140 graphs of varying complexity.
HeQ: a Large and Diverse Hebrew Reading Comprehension Benchmark (2023.findings-emnlp)

Copied to clipboard

Challenge: Current benchmarks for Hebrew Natural Language Processing (NLP) focus mainly on morpho-syntactic tasks, neglecting the semantic dimension of language understanding.
Approach: They propose to use Hebrew machine reading comprehension (MRC) as extractive Question Answering to address this problem.
Outcome: The proposed benchmark features 30,147 question-answer pairs derived from both Hebrew Wikipedia articles and Israeli tech news.
Quoref: A Reading Comprehension Dataset with Questions Requiring Coreferential Reasoning (D19-1)

Copied to clipboard

Challenge: Existing reading comprehension benchmarks do not contain complex coreferential phenomena . obtaining questions focused on such phenomena is difficult because of lexical cues .
Approach: They propose to use a crowdsourced dataset to examine the ability of models to resolve coreference among entities in Wikipedia paragraphs.
Outcome: The proposed model performs significantly worse than humans on the reading comprehension benchmark . paragraphs and other longer texts typically make multiple references to the same entities .
BanglaRQA: A Benchmark Dataset for Under-resourced Bangla Language Reading Comprehension-based Question Answering with Diverse Question-Answer Types (2022.findings-emnlp)

Copied to clipboard

Challenge: a lack of diverse and comprehensive question-answering datasets exists in under-resourced languages like Bangla.
Approach: They propose a reading comprehension-based Bangla question-answering dataset . the dataset includes answerable and unanswerable questions covering four categories of questions .
Outcome: The proposed dataset shows that it performs well as a training resource in high-resource languages.
SciMRC: Multi-perspective Scientific Machine Reading Comprehension (2024.lrec-main)

Copied to clipboard

Challenge: Existing datasets focused on single-perspective question-answer pairs overlooking inherent variation in comprehension levels among different readers.
Approach: They propose a multi-perspective scientific machine reading comprehension dataset . their dataset comprises 741 scientific papers and 6,057 question-answer pairs .
Outcome: The proposed dataset includes questions from beginners, students, and experts.
SKA-Bench: A Fine-Grained Benchmark for Evaluating Structured Knowledge Understanding of LLMs (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing evaluations for Structured Knowledge (SK) understanding are non-rigorous and focus on a single type of SK.
Approach: They propose a structured knowledge understanding benchmark that includes four widely used structured knowledge forms.
Outcome: The proposed benchmark is based on four widely used structured knowledge forms . it includes a question, an answer, positive knowledge units, and noisy knowledge units .
KRISTEVA: Close Reading as a Novel Task for Benchmarking Interpretive Reasoning (2025.acl-long)

Copied to clipboard

Challenge: a study of close reading skills in large language models (LLMs) shows that LLMs still lag behind human evaluators on 10 of 11 tasks.
Approach: They propose a benchmark to evaluate close reading skills in large language models . they propose three tasks to approximate different elements of the close reading process .
Outcome: The proposed benchmarks show that state-of-the-art LLMs possess some college-level close reading competency, but performance still trails human evaluators on 10 out of 11 tasks.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations