Cover Image

On the Sensitivity of Instruction-tuned LLMs to Harmful Sentences in Long Inputs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ghorbanpour, Faeze, Fraser, Alexander
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Computers and Society
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Can Prompting LLMs Unlock Hate Speech Detection across Languages? A Zero-shot and Few-shot Study
by: Ghorbanpour, Faeze, et al.
Published: (2025)

Data-Efficient Hate Speech Detection via Cross-Lingual Nearest Neighbor Retrieval with Limited Labeled Data
by: Ghorbanpour, Faeze, et al.
Published: (2025)

PersLitEval: Fine-grained Benchmark and Evaluation of LLMs on Persian Literature Questions
by: Niazi, Ruhallah, et al.
Published: (2026)

Are BabyLMs Second Language Learners?
by: Edman, Lukas, et al.
Published: (2024)

Hate Personified: Investigating the role of LLMs in content moderation
by: Masud, Sarah, et al.
Published: (2024)

Between Help and Harm: An Evaluation of Mental Health Crisis Handling by LLMs
by: Arnaiz-Rodriguez, Adrian, et al.
Published: (2025)

Do Prevalent Bias Metrics Capture Allocational Harms from LLMs?
by: Cyberey, Hannah, et al.
Published: (2024)

Diverse, but Divisive: LLMs Can Exaggerate Gender Differences in Opinion Related to Harms of Misinformation
by: Neumann, Terrence, et al.
Published: (2024)

HRIPBench: Benchmarking LLMs in Harm Reduction Information Provision to Support People Who Use Drugs
by: Wang, Kaixuan, et al.
Published: (2025)

Prompt Refinement or Fine-tuning? Best Practices for using LLMs in Computational Social Science Tasks
by: Møller, Anders Giovanni, et al.
Published: (2024)

Survival at Any Cost? LLMs and the Choice Between Self-Preservation and Human Harm
by: Mohamadi, Alireza, et al.
Published: (2025)

QueerGen: How LLMs Reflect Societal Norms on Gender and Sexuality in Sentence Completion Tasks
by: Sosto, Mae, et al.
Published: (2026)

Careless Whisper: Speech-to-Text Hallucination Harms
by: Koenecke, Allison, et al.
Published: (2024)

Differentiating Emigration from Return Migration of Scholars Using Name-Based Nationality Detection Models
by: Ghorbanpour, Faeze, et al.
Published: (2025)

Accommodation and Epistemic Vigilance: A Pragmatic Account of Why LLMs Fail to Challenge Harmful Beliefs
by: Cheng, Myra, et al.
Published: (2026)

Unintended Harms of Value-Aligned LLMs: Psychological and Empirical Insights
by: Choi, Sooyung, et al.
Published: (2025)

Taxonomizing Representational Harms using Speech Act Theory
by: Corvi, Emily, et al.
Published: (2025)

LLM-based Semantic Augmentation for Harmful Content Detection
by: Meguellati, Elyas, et al.
Published: (2025)

Expected Harm: Rethinking Safety Evaluation of (Mis)Aligned LLMs
by: Chen, Yen-Shan, et al.
Published: (2026)

PluriHarms: Benchmarking the Full Spectrum of Human Judgments on AI Harm
by: Li, Jing-Jing, et al.
Published: (2026)

A Capabilities Approach to Studying Bias and Harm in Language Technologies
by: Nigatu, Hellina Hailu, et al.
Published: (2024)

The Hidden Language of Harm: Examining the Role of Emojis in Harmful Online Communication and Content Moderation
by: Zhou, Yuhang, et al.
Published: (2025)

Speak Easy: Eliciting Harmful Jailbreaks from LLMs with Simple Interactions
by: Chan, Yik Siu, et al.
Published: (2025)

Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM
by: Zhang, Chi, et al.
Published: (2025)

Harmful Speech Detection by Language Models Exhibits Gender-Queer Dialect Bias
by: Dorn, Rebecca, et al.
Published: (2024)

From Representational Harms to Quality-of-Service Harms: A Case Study on Llama 2 Safety Safeguards
by: Chehbouni, Khaoula, et al.
Published: (2024)

Creativity Support in the Age of Large Language Models: An Empirical Study Involving Emerging Writers
by: Chakrabarty, Tuhin, et al.
Published: (2023)

From Judgment to Interference: Early Stopping LLM Harmful Outputs via Streaming Content Monitoring
by: Li, Yang, et al.
Published: (2025)

Understanding and Meeting Practitioner Needs When Measuring Representational Harms Caused by LLM-Based Systems
by: Harvey, Emma, et al.
Published: (2025)

Exploring LLMs for Predicting Tutor Strategy and Student Outcomes in Dialogues
by: Ikram, Fareya, et al.
Published: (2025)

Detecting AI-Generated Text: Factors Influencing Detectability with Current Methods
by: Fraser, Kathleen C., et al.
Published: (2024)

What do Large Language Models Say About Animals? Investigating Risks of Animal Harm in Generated Text
by: Kanepajs, Arturs, et al.
Published: (2025)

Who Decides What Is Harmful? Content Moderation Policy Through A Multi-Agent Personalised Inference Framework
by: Gajewska, Ewelina, et al.
Published: (2026)

People Make Better Edits: Measuring the Efficacy of LLM-Generated Counterfactually Augmented Data for Harmful Language Detection
by: Sen, Indira, et al.
Published: (2023)

GPT-HateCheck: Can LLMs Write Better Functional Tests for Hate Speech Detection?
by: Jin, Yiping, et al.
Published: (2024)

Challenging Negative Gender Stereotypes: A Study on the Effectiveness of Automated Counter-Stereotypes
by: Nejadgholi, Isar, et al.
Published: (2024)

Fine-tuning with Hierarchical Prompting for Robust Propaganda Classification Across Annotation Schemas
by: Stähelin, Lukas, et al.
Published: (2026)

Topic Modeling with Fine-tuning LLMs and Bag of Sentences
by: Schneider, Johannes
Published: (2024)

Beyond Single-Sentence Prompts: Upgrading Value Alignment Benchmarks with Dialogues and Stories
by: Zhang, Yazhou, et al.
Published: (2025)

RoleConflictBench: A Benchmark of Role Conflict Scenarios for Evaluating LLMs' Contextual Sensitivity
by: Shin, Jisu, et al.
Published: (2025)