paper-with-me

Papers

Dissecting Dissonance: Benchmarking Large Multimodal Models Against Self-Contradictory Instructions

2024-08-02 · Jin Gao, Lei Gan, Yuankai Li, Yixin Ye, Dequan Wang

Large multimodal models (LMMs) excel in adhering to human instructions. However, self-contradictory instructions may arise due to the increasing trend of multimodal interaction and context length, which is challenging for language beginners and vulnerable populations. We introduce the Self-Contradictory Instructions benchmark to evaluate the capability of LMMs in recognizing conflicting commands. It comprises 20,000 conflicts, evenly distributed between language and vision paradigms. It is constructed by a novel automatic dataset creation framework, which expedites the process and enables us to encompass a wide range of instruction forms. Our comprehensive evaluation reveals current LMMs consistently struggle to identify multimodal instruction discordance due to a lack of self-awareness. Hence, we propose the Cognitive Awakening Prompting to inject cognition from external, largely enhancing dissonance detection. The dataset and code are here: https://selfcontradiction.github.io/.

📄 PDF Abstract BibTeX arXiv:2408.01091

Code (1)

shiyegao/Self-Contradictory-Instructions-SCI 공식 구현

Tasks

Benchmarkingmultimodal interaction

Similar Papers 제목 키워드 기반

Topic-independent Detection of Dissonance in Short Stance Text

2021-06-16 · ACL ARR Jun 2021 6 · Anonymous

We address dissonance detection, the task of detecting conflicting stance between two input statements. Computational models for stance detection have typically been trained for a given target topic (e.g. gun control). I…

Stance Detection

Empirical Evaluation of Topic Zero- and Few-Shot Learning for Stance Dissonance Detection

2021-11-16 · ACL ARR November 2021 11 · Anonymous

We address stance dissonance detection, the task of detecting conflicting stance between two input statements. Computational models for traditional stance detection have typically been trained to indicate pro/cons for a …

Few-Shot LearningStance Detection

Characterizing Social Imaginaries and Self-Disclosures of Dissonance in Online Conspiracy Discussion Communities

2021-07-21 · Shruti Phadke, Mattia Samory, Tanushree Mitra

Online discussion platforms offer a forum to strengthen and propagate belief in misinformed conspiracy theories. Yet, they also offer avenues for conspiracy theorists to express their doubts and experiences of cognitive …

2k

Benchmarking Large Multimodal Models against Common Corruptions

2024-01-22 · Jiawei Zhang, Tianyu Pang, Chao Du, Yi Ren 외

This technical report aims to fill a deficiency in the assessment of large multimodal models (LMMs) by specifically examining the self-consistency of their outputs when subjected to common corruptions. We investigate the…

BenchmarkingImage to textSpeech-to-Texttext-to-speech+1

From Dissonance to Insights: Dissecting Disagreements in Rationale Construction for Case Outcome Classification

2023-10-18 · Shanshan Xu, T. Y. S. S Santosh, Oana Ichim, Isabella Risini 외

In legal NLP, Case Outcome Classification (COC) must not only be accurate but also trustworthy and explainable. Existing work in explainable COC has been limited to annotations by a single expert. However, it is well-kno…