Copertina

Engagement Undermines Safety: How Stereotypes and Toxicity Shape Humor in Language Models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Dogra, Atharvan, Ghosal, Soumya Suvra, Deshpande, Ameet, Kalyan, Ashwin, Manocha, Dinesh
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Language Models can Subtly Deceive Without Lying: A Case Study on Strategic Phrasing in Legislation
di: Dogra, Atharvan, et al.
Pubblicazione: (2024)

PromptRefine: Enhancing Few-Shot Performance on Low-Resource Indic Languages with Example Selection from Related Example Banks
di: Ghosal, Soumya Suvra, et al.
Pubblicazione: (2024)

Safety Recovery in Reasoning Models Is Only a Few Early Steering Steps Away
di: Ghosal, Soumya Suvra, et al.
Pubblicazione: (2026)

Relic: Enhancing Reward Model Generalization for Low-Resource Indic Languages with Few-Shot Examples
di: Ghosal, Soumya Suvra, et al.
Pubblicazione: (2025)

IntCoOp: Interpretability-Aware Vision-Language Prompt Tuning
di: Ghosal, Soumya Suvra, et al.
Pubblicazione: (2024)

Probing AI Safety with Source Code
di: Narayan, Ujwal, et al.
Pubblicazione: (2025)

Bounded Rationality for LLMs: Satisficing Alignment at Inference-Time
di: Chehade, Mohamad, et al.
Pubblicazione: (2025)

Transfer Q Star: Principled Decoding for LLM Alignment
di: Chakraborty, Souradip, et al.
Pubblicazione: (2024)

Does Thinking More always Help? Mirage of Test-Time Scaling in Reasoning Models
di: Ghosal, Soumya Suvra, et al.
Pubblicazione: (2025)

Bias Runs Deep: Implicit Reasoning Biases in Persona-Assigned LLMs
di: Gupta, Shashank, et al.
Pubblicazione: (2023)

QualEval: Qualitative Evaluation for Model Improvement
di: Murahari, Vishvak, et al.
Pubblicazione: (2023)

Collab: Controlled Decoding using Mixture of Agents for LLM Alignment
di: Chakraborty, Souradip, et al.
Pubblicazione: (2025)

KITE: Kernelized and Information Theoretic Exemplars for In-Context Learning
di: Singh, Vaibhav, et al.
Pubblicazione: (2025)

Agent Context Protocols Enhance Collective Inference
di: Bhardwaj, Devansh, et al.
Pubblicazione: (2025)

Compromesso! Italian Many-Shot Jailbreaks Undermine the Safety of Large Language Models
di: Pernisi, Fabio, et al.
Pubblicazione: (2024)

Text Is Not All You Need: Multimodal Prompting Helps LLMs Understand Humor
di: Baluja, Ashwin
Pubblicazione: (2024)

RLHF Deciphered: A Critical Analysis of Reinforcement Learning from Human Feedback for LLMs
di: Chaudhari, Shreyas, et al.
Pubblicazione: (2024)

PersonaGym: Evaluating Persona Agents and LLMs
di: Samuel, Vinay, et al.
Pubblicazione: (2024)

Augmenting Lateral Thinking in Language Models with Humor and Riddle Data for the BRAINTEASER Task
di: Ghashami, Mina, et al.
Pubblicazione: (2024)

Analyzing the Safety of Japanese Large Language Models in Stereotype-Triggering Prompts
di: Nakanishi, Akito, et al.
Pubblicazione: (2025)

Reading Between the Prompts: How Stereotypes Shape LLM's Implicit Personalization
di: Neplenbroek, Vera, et al.
Pubblicazione: (2025)

Do Vision-Language Models Understand Compound Nouns?
di: Kumar, Sonal, et al.
Pubblicazione: (2024)

The Reliability Paradox: Exploring How Shortcut Learning Undermines Language Model Calibration
di: Bihani, Geetanjali, et al.
Pubblicazione: (2024)

Quantifying Stereotypes in Language
di: Liu, Yang
Pubblicazione: (2024)

HumorRank: A Tournament-Based Leaderboard for Evaluating Humor Generation in Large Language Models
di: Ajayi, Edward, et al.
Pubblicazione: (2026)

HumorGen: Cognitive Synergy for Humor Generation in Large Language Models via Persona-Based Distillation
di: Ajayi, Edward, et al.
Pubblicazione: (2026)

Fragile Mastery: Are Domain-Specific Trade-Offs Undermining On-Device Language Models?
di: Jha, Basab, et al.
Pubblicazione: (2025)

What Drives Representation Steering? A Mechanistic Case Study on Steering Refusal
di: Cheng, Stephen, et al.
Pubblicazione: (2026)

Measuring Stereotype and Deviation Biases in Large Language Models
di: Wang, Daniel, et al.
Pubblicazione: (2025)

Systematic Offensive Stereotyping (SOS) Bias in Language Models
di: Elsafoury, Fatma
Pubblicazione: (2023)

Bypassing Safety Guardrails in LLMs Using Humor
di: Cisneros-Velarde, Pedro
Pubblicazione: (2025)

Natural Context Drift Undermines the Natural Language Understanding of Large Language Models
di: Wu, Yulong, et al.
Pubblicazione: (2025)

Do Multilingual Large Language Models Mitigate Stereotype Bias?
di: Nie, Shangrui, et al.
Pubblicazione: (2024)

ELITE: Enhanced Language-Image Toxicity Evaluation for Safety
di: Lee, Wonjun, et al.
Pubblicazione: (2025)

Getting Serious about Humor: Crafting Humor Datasets with Unfunny Large Language Models
di: Horvitz, Zachary, et al.
Pubblicazione: (2024)

Toxicity Red-Teaming: Benchmarking LLM Safety in Singapore's Low-Resource Languages
di: Hu, Yujia, et al.
Pubblicazione: (2025)

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation
di: Zhang, Zhibo, et al.
Pubblicazione: (2025)

How Toxic Can You Get? Search-based Toxicity Testing for Large Language Models
di: Corbo, Simone, et al.
Pubblicazione: (2025)

CFunModel: A "Funny" Language Model Capable of Chinese Humor Generation and Processing
di: Yu, Zhenghan, et al.
Pubblicazione: (2025)

Women Are Beautiful, Men Are Leaders: Gender Stereotypes in Machine Translation and Language Modeling
di: Pikuliak, Matúš, et al.
Pubblicazione: (2023)