Benchmarking Gaslighting Negation Attacks Against Reasoning Models
Authors:
- Bin ZhuBZBin Zhu
- Hailong YinHYHailong Yin
- Jingjing ChenJCJingjing Chen
- Yu-Gang JiangYJYu-Gang Jiang
- 6 February 2026
- book chapter
- Published by Springer Nature
- p. 188-202
Abstract
No abstract availableKeywords
This publication has 11 references indexed in Scilit:
- Vision-Language Models Do Not Understand Negation2025
- Aligning Large Language Models for Faithful Integrity Against Opposing ArgumentProceedings of the AAAI Conference on Artificial Intelligence, 2025
- Improved Baselines with Visual Instruction Tuning2024
- MMMU: A Massive Multi-Discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI2024
- CLIPN for Zero-Shot OOD Detection: Teaching CLIP to Say No2023
- Can ChatGPT Defend its Belief in Truth? Evaluating LLM Reasoning via Debate2023
- Language models are not naysayers: an analysis of language models on negation benchmarks2023
- What BERT Is Not: Lessons from a New Suite of Psycholinguistic Diagnostics for Language ModelsTransactions of the Association for Computational Linguistics, 2020
- Negated and Misprimed Probes for Pretrained Language Models: Birds Can Talk, But Cannot Fly2020
- Injecting Numerical Reasoning Skills into Language Models2020