Image de couverture de livre

Redirected, Not Removed: Task-Dependent Stereotyping Reveals the Limits of LLM Alignments

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Kumar, Divyanshu, Gupta, Ishita, Birur, Nitin Aravind, Baswa, Tanay, Agarwal, Sahil, Harshangi, Prashanth
Format:	Preprint
Publié:	2026
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

SocioEval: A Template-Based Framework for Evaluating Socioeconomic Status Bias in Foundation Models
par: Kumar, Divyanshu, et autres
Publié: (2026)

Beyond Western Politics: Cross-Cultural Benchmarks for Evaluating Partisan Associations in LLMs
par: Kumar, Divyanshu, et autres
Publié: (2025)

VERA: Validation and Enhancement for Retrieval Augmented systems
par: Birur, Nitin Aravind, et autres
Publié: (2024)

SAGE-RT: Synthetic Alignment data Generation for Safety Evaluation and Red Teaming
par: Kumar, Anurakt, et autres
Publié: (2024)

No Free Lunch with Guardrails
par: Kumar, Divyanshu, et autres
Publié: (2025)

Quantifying CBRN Risk in Frontier Models
par: Kumar, Divyanshu, et autres
Publié: (2025)

Beyond Text: Multimodal Jailbreaking of Vision-Language and Audio Models through Perceptually Simple Transformations
par: Kumar, Divyanshu, et autres
Publié: (2025)

Investigating Implicit Bias in Large Language Models: A Large-Scale Study of Over 50 LLMs
par: Kumar, Divyanshu, et autres
Publié: (2024)

Fine-Tuning, Quantization, and LLMs: Navigating Unintended Outcomes
par: Kumar, Divyanshu, et autres
Publié: (2024)

Ethical Reasoning and Moral Value Alignment of LLMs Depend on the Language we Prompt them in
par: Agarwal, Utkarsh, et autres
Publié: (2024)

PLANTS: A Novel Problem and Dataset for Summarization of Planning-Like (PL) Tasks
par: Pallagani, Vishal, et autres
Publié: (2024)

Languages are Modalities: Cross-Lingual Alignment via Encoder Injection
par: Agarwal, Rajan, et autres
Publié: (2025)

Curiosity-Driven LLM-as-a-judge for Personalized Creative Judgment
par: Kumar, Vanya Bannihatti, et autres
Publié: (2025)

DECASTE: Unveiling Caste Stereotypes in Large Language Models through Multi-Dimensional Bias Analysis
par: Vijayaraghavan, Prashanth, et autres
Publié: (2025)

Personality Shapes Gender Bias in Persona-Conditioned LLM Narratives Across English and Hindi: An Empirical Investigation
par: Kumar, Tanay, et autres
Publié: (2026)

Dual Debiasing: Remove Stereotypes and Keep Factual Gender for Fair Language Modeling and Translation
par: Limisiewicz, Tomasz, et autres
Publié: (2025)

Diagnosing the Performance Trade-off in Moral Alignment: A Case Study on Gender Stereotypes
par: Liu, Guangliang, et autres
Publié: (2025)

Probing the Limits of Stylistic Alignment in Vision-Language Models
par: Farajidizaji, Asma, et autres
Publié: (2025)

JEBS: A Fine-grained Biomedical Lexical Simplification Task
par: Xia, William, et autres
Publié: (2025)

Do Language Models Know When They'll Refuse? Probing Introspective Awareness of Safety Boundaries
par: Gondil, Tanay
Publié: (2026)

Reading Between the Prompts: How Stereotypes Shape LLM's Implicit Personalization
par: Neplenbroek, Vera, et autres
Publié: (2025)

Simulating Identity, Propagating Bias: Abstraction and Stereotypes in LLM-Generated Text
par: Sommerauer, Pia, et autres
Publié: (2025)

Exploring the Limits of Fine-grained LLM-based Physics Inference via Premise Removal Interventions
par: Meadows, Jordan, et autres
Publié: (2024)

Quantifying Stereotypes in Language
par: Liu, Yang
Publié: (2024)

LLM Task Interference: An Initial Study on the Impact of Task-Switch in Conversational History
par: Gupta, Akash, et autres
Publié: (2024)

Team A at SemEval-2025 Task 11: Breaking Language Barriers in Emotion Detection with Multilingual Models
par: Sahil, P Sam, et autres
Publié: (2025)

Challenging Negative Gender Stereotypes: A Study on the Effectiveness of Automated Counter-Stereotypes
par: Nejadgholi, Isar, et autres
Publié: (2024)

Stereotype Detection as a Catalyst for Enhanced Bias Detection: A Multi-Task Learning Approach
par: Tomar, Aditya, et autres
Publié: (2025)

AlphaPO: Reward Shape Matters for LLM Alignment
par: Gupta, Aman, et autres
Publié: (2025)

Examining Alignment of Large Language Models through Representative Heuristics: The Case of Political Stereotypes
par: Jeoung, Sullam, et autres
Publié: (2025)

Human-Instruction-Free LLM Self-Alignment with Limited Samples
par: Guo, Hongyi, et autres
Publié: (2024)

LLM driven Text-to-Table Generation through Sub-Tasks Guidance and Iterative Refinement
par: C, Rajmohan, et autres
Publié: (2025)

Ask Early, Ask Late, Ask Right: When Does Clarification Timing Matter for Long-Horizon Agents?
par: Gulati, Anmol, et autres
Publié: (2026)

Systematic Evaluation of LLM-as-a-Judge in LLM Alignment Tasks: Explainable Metrics and Diverse Prompt Templates
par: Wei, Hui, et autres
Publié: (2024)

Task-Dependent Evaluation of LLM Output Homogenization: A Taxonomy-Guided Framework
par: Jain, Shomik, et autres
Publié: (2025)

Investigating Gender Bias in LLM-Generated Stories via Psychological Stereotypes
par: Masoudian, Shahed, et autres
Publié: (2025)

'Since Lawyers are Males..': Examining Implicit Gender Bias in Hindi Language Generation by LLMs
par: Joshi, Ishika, et autres
Publié: (2024)

LLM for Barcodes: Generating Diverse Synthetic Data for Identity Documents
par: Patel, Hitesh Laxmichand, et autres
Publié: (2024)

Semantic similarity estimation for domain specific data using BERT and other techniques
par: Prashanth, R.
Publié: (2025)

Understanding Student Sentiment on Mental Health Support in Colleges Using Large Language Models
par: Sood, Palak, et autres
Publié: (2024)