BeDiscovER: The Benchmark of Discourse Understanding in the Era of Reasoning Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Chuyuan, Carenini, Giuseppe
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915754678419456
author Li, Chuyuan
Carenini, Giuseppe
author_facet Li, Chuyuan
Carenini, Giuseppe
contents We introduce BeDiscovER (Benchmark of Discourse Understanding in the Era of Reasoning Language Models), an up-to-date, comprehensive suite for evaluating the discourse-level knowledge of modern LLMs. BeDiscovER compiles 5 publicly available discourse tasks across discourse lexicon, (multi-)sentential, and documental levels, with in total 52 individual datasets. It covers both extensively studied tasks such as discourse parsing and temporal relation extraction, as well as some novel challenges such as discourse particle disambiguation (e.g., ``just''), and also aggregates a shared task on Discourse Relation Parsing and Treebanking for multilingual and multi-framework discourse relation classification. We evaluate open-source LLMs: Qwen3 series, DeepSeek-R1, and frontier model such as GPT-5-mini on BeDiscovER, and find that state-of-the-art models exhibit strong performance in arithmetic aspect of temporal reasoning, but they struggle with full document reasoning and some subtle semantic and discourse phenomena, such as rhetorical relation recognition.
format Preprint
id arxiv_https___arxiv_org_abs_2511_13095
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle BeDiscovER: The Benchmark of Discourse Understanding in the Era of Reasoning Language Models
Li, Chuyuan
Carenini, Giuseppe
Computation and Language
We introduce BeDiscovER (Benchmark of Discourse Understanding in the Era of Reasoning Language Models), an up-to-date, comprehensive suite for evaluating the discourse-level knowledge of modern LLMs. BeDiscovER compiles 5 publicly available discourse tasks across discourse lexicon, (multi-)sentential, and documental levels, with in total 52 individual datasets. It covers both extensively studied tasks such as discourse parsing and temporal relation extraction, as well as some novel challenges such as discourse particle disambiguation (e.g., ``just''), and also aggregates a shared task on Discourse Relation Parsing and Treebanking for multilingual and multi-framework discourse relation classification. We evaluate open-source LLMs: Qwen3 series, DeepSeek-R1, and frontier model such as GPT-5-mini on BeDiscovER, and find that state-of-the-art models exhibit strong performance in arithmetic aspect of temporal reasoning, but they struggle with full document reasoning and some subtle semantic and discourse phenomena, such as rhetorical relation recognition.
title BeDiscovER: The Benchmark of Discourse Understanding in the Era of Reasoning Language Models
topic Computation and Language
url https://arxiv.org/abs/2511.13095