natural-language-processing-11

Fact Selection

3260 papers • 126 benchmarks • 313 datasets

A task where an agent should select at most two sentences from the paper as argumentative facts.

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in fact-selection-11

Trend

Dataset

Best Model

Actions

ArgSciChat

Libraries

i

Use these libraries to find fact-selection-11 models and implementations

Datasets

ArgSciChat

Subtasks

No subtasks available.

Most implemented papers

ArgSciChat: A Dataset for Argumentative Dialogues on Scientific Papers

Iryna Gurevych, Federico Ruggeri, Mohsen Mesgar•Sun Feb 13 2022

A novel framework to collect dialogues between scientists as domain experts on scientific papers and lets scientists present their scientific papers as groundings for dialogues and participate in dialogue they like its paper title is introduced.

2

Content

0

Paper Graph

FaiRR: Faithful and Robust Deductive Reasoning over Natural Language

Harman Singh, Xiang Ren, Soumya Sanyal•Fri Mar 18 2022

This work frames the deductive logical reasoning task by defining three modular components: rule selection, fact selection, and knowledge composition, and proposes FaiRR (Faithful and Robust Reasoner), which is robust to novel language perturbations, and is faster at inference than previous works on existing reasoning datasets.

48 0

Paper Graph

COVID-VTS: Fact Extraction and Verification on Short Video Platforms

Abhinav Shrivastava, Fuxiao Liu, Y. Yacoob•Tue Feb 14 2023

TwtrDetective is proposed, an effective model incorporating cross-media consistency checking to detect token-level malicious tampering in different modalities, and generate explanations to automatically generate misleading video posts by event manipulation or adversarial matching.

37 0

Paper Graph

Expository Text Generation: Imitate, Retrieve, Paraphrase

Jie Huang, K. Chang, Nishant Balepur•Thu May 04 2023

This work develops IRP, a framework that overcomes the limitations of retrieval-augmented models and iteratively performs content planning, fact retrieval, and rephrasing and shows that IRP produces factual and organized expository texts that accurately inform readers.

12 0

Paper Graph

UFO: Unified Fact Obtaining for Commonsense Question Answering

Zhifeng Li, Yifan Fan, Bowei Zou, Yu Hong•Wed May 24 2023

The proposed Unified Facts Obtaining approach turns LLMs into knowledge sources and produces relevant facts (knowledge statements) for the given question and significantly improves the performance of the inference model and outperforms manually constructed knowledge sources.

1 0

Paper Graph

Integrating Randomness in Large Language Models: A Linear Congruential Generator Approach for Generating Clinically Relevant Content

Andrew Bouras•Wed Jul 03 2024

This method addresses key issues of randomness and repetition, enhancing the quality and efficiency of language model-generated content for various applications.

7 0

Paper Graph

Adding a benchmark result helps the community track progress.