Cover Image

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

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Kumar, Divyanshu, Gupta, Ishita, Birur, Nitin Aravind, Baswa, Tanay, Agarwal, Sahil, Harshangi, Prashanth
Format:	Preprint
Published:	2026
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

SocioEval: A Template-Based Framework for Evaluating Socioeconomic Status Bias in Foundation Models
by: Kumar, Divyanshu, et al.
Published: (2026)

Beyond Western Politics: Cross-Cultural Benchmarks for Evaluating Partisan Associations in LLMs
by: Kumar, Divyanshu, et al.
Published: (2025)

VERA: Validation and Enhancement for Retrieval Augmented systems
by: Birur, Nitin Aravind, et al.
Published: (2024)

SAGE-RT: Synthetic Alignment data Generation for Safety Evaluation and Red Teaming
by: Kumar, Anurakt, et al.
Published: (2024)

No Free Lunch with Guardrails
by: Kumar, Divyanshu, et al.
Published: (2025)

Quantifying CBRN Risk in Frontier Models
by: Kumar, Divyanshu, et al.
Published: (2025)

Beyond Text: Multimodal Jailbreaking of Vision-Language and Audio Models through Perceptually Simple Transformations
by: Kumar, Divyanshu, et al.
Published: (2025)

Investigating Implicit Bias in Large Language Models: A Large-Scale Study of Over 50 LLMs
by: Kumar, Divyanshu, et al.
Published: (2024)

Fine-Tuning, Quantization, and LLMs: Navigating Unintended Outcomes
by: Kumar, Divyanshu, et al.
Published: (2024)

Ethical Reasoning and Moral Value Alignment of LLMs Depend on the Language we Prompt them in
by: Agarwal, Utkarsh, et al.
Published: (2024)

PLANTS: A Novel Problem and Dataset for Summarization of Planning-Like (PL) Tasks
by: Pallagani, Vishal, et al.
Published: (2024)

Languages are Modalities: Cross-Lingual Alignment via Encoder Injection
by: Agarwal, Rajan, et al.
Published: (2025)

Curiosity-Driven LLM-as-a-judge for Personalized Creative Judgment
by: Kumar, Vanya Bannihatti, et al.
Published: (2025)

DECASTE: Unveiling Caste Stereotypes in Large Language Models through Multi-Dimensional Bias Analysis
by: Vijayaraghavan, Prashanth, et al.
Published: (2025)

Personality Shapes Gender Bias in Persona-Conditioned LLM Narratives Across English and Hindi: An Empirical Investigation
by: Kumar, Tanay, et al.
Published: (2026)

Dual Debiasing: Remove Stereotypes and Keep Factual Gender for Fair Language Modeling and Translation
by: Limisiewicz, Tomasz, et al.
Published: (2025)

Diagnosing the Performance Trade-off in Moral Alignment: A Case Study on Gender Stereotypes
by: Liu, Guangliang, et al.
Published: (2025)

Probing the Limits of Stylistic Alignment in Vision-Language Models
by: Farajidizaji, Asma, et al.
Published: (2025)

JEBS: A Fine-grained Biomedical Lexical Simplification Task
by: Xia, William, et al.
Published: (2025)

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

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

Simulating Identity, Propagating Bias: Abstraction and Stereotypes in LLM-Generated Text
by: Sommerauer, Pia, et al.
Published: (2025)

Exploring the Limits of Fine-grained LLM-based Physics Inference via Premise Removal Interventions
by: Meadows, Jordan, et al.
Published: (2024)

Quantifying Stereotypes in Language
by: Liu, Yang
Published: (2024)

LLM Task Interference: An Initial Study on the Impact of Task-Switch in Conversational History
by: Gupta, Akash, et al.
Published: (2024)

Team A at SemEval-2025 Task 11: Breaking Language Barriers in Emotion Detection with Multilingual Models
by: Sahil, P Sam, et al.
Published: (2025)

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

Stereotype Detection as a Catalyst for Enhanced Bias Detection: A Multi-Task Learning Approach
by: Tomar, Aditya, et al.
Published: (2025)

AlphaPO: Reward Shape Matters for LLM Alignment
by: Gupta, Aman, et al.
Published: (2025)

Examining Alignment of Large Language Models through Representative Heuristics: The Case of Political Stereotypes
by: Jeoung, Sullam, et al.
Published: (2025)

Human-Instruction-Free LLM Self-Alignment with Limited Samples
by: Guo, Hongyi, et al.
Published: (2024)

LLM driven Text-to-Table Generation through Sub-Tasks Guidance and Iterative Refinement
by: C, Rajmohan, et al.
Published: (2025)

Ask Early, Ask Late, Ask Right: When Does Clarification Timing Matter for Long-Horizon Agents?
by: Gulati, Anmol, et al.
Published: (2026)

Systematic Evaluation of LLM-as-a-Judge in LLM Alignment Tasks: Explainable Metrics and Diverse Prompt Templates
by: Wei, Hui, et al.
Published: (2024)

Task-Dependent Evaluation of LLM Output Homogenization: A Taxonomy-Guided Framework
by: Jain, Shomik, et al.
Published: (2025)

Investigating Gender Bias in LLM-Generated Stories via Psychological Stereotypes
by: Masoudian, Shahed, et al.
Published: (2025)

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

LLM for Barcodes: Generating Diverse Synthetic Data for Identity Documents
by: Patel, Hitesh Laxmichand, et al.
Published: (2024)

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

Understanding Student Sentiment on Mental Health Support in Colleges Using Large Language Models
by: Sood, Palak, et al.
Published: (2024)