Cover Image

Attributional Safety Failures in Large Language Models under Code-Mixed Perturbations

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Banerjee, Somnath, Chatterjee, Pratyush, Kumar, Shanu, Layek, Sayan, Agrawal, Parag, Hazra, Rima, Mukherjee, Animesh
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Soteria: Language-Specific Functional Parameter Steering for Multilingual Safety Alignment
by: Banerjee, Somnath, et al.
Published: (2025)

SafeInfer: Context Adaptive Decoding Time Safety Alignment for Large Language Models
by: Banerjee, Somnath, et al.
Published: (2024)

Navigating the Cultural Kaleidoscope: A Hitchhiker's Guide to Sensitivity in Large Language Models
by: Banerjee, Somnath, et al.
Published: (2024)

How (un)ethical are instruction-centric responses of LLMs? Unveiling the vulnerabilities of safety guardrails to harmful queries
by: Banerjee, Somnath, et al.
Published: (2024)

Safety Arithmetic: A Framework for Test-time Safety Alignment of Language Models by Steering Parameters and Activations
by: Hazra, Rima, et al.
Published: (2024)

ProSocialAlign: Preference Conditioned Test Time Alignment in Language Models
by: Banerjee, Somnath, et al.
Published: (2025)

Bridging the Multilingual Safety Divide: Efficient, Culturally-Aware Alignment for Global South Languages
by: Banerjee, Somnath, et al.
Published: (2026)

AURA: Affordance-Understanding and Risk-aware Alignment Technique for Large Language Models
by: Adak, Sayantan, et al.
Published: (2025)

Sowing the Wind, Reaping the Whirlwind: The Impact of Editing Language Models
by: Hazra, Rima, et al.
Published: (2024)

Context Matters: Pushing the Boundaries of Open-Ended Answer Generation with Graph-Structured Knowledge Context
by: Banerjee, Somnath, et al.
Published: (2024)

Breaking Boundaries: Investigating the Effects of Model Editing on Cross-linguistic Performance
by: Banerjee, Somnath, et al.
Published: (2024)

MemeSense: An Adaptive In-Context Framework for Social Commonsense Driven Meme Moderation
by: Adak, Sayantan, et al.
Published: (2025)

DistALANER: Distantly Supervised Active Learning Augmented Named Entity Recognition in the Open Source Software Ecosystem
by: Banerjee, Somnath, et al.
Published: (2024)

Lost in Interpretation: The Plausibility-Faithfulness Trade-off in Cross-Lingual Explanations
by: Banerjee, Somnath, et al.
Published: (2026)

Evaluating the Ebb and Flow: An In-depth Analysis of Question-Answering Trends across Diverse Platforms
by: Hazra, Rima, et al.
Published: (2023)

SafeMath: Inference-time Safety improves Math Accuracy
by: Basu, Sagnik, et al.
Published: (2026)

SafeTutors: Benchmarking Pedagogical Safety in AI Tutoring Systems
by: Hazra, Rima, et al.
Published: (2026)

Redefining Developer Assistance: Through Large Language Models in Software Ecosystem
by: Banerjee, Somnath, et al.
Published: (2023)

From Fluent to Verifiable: Claim-Level Auditability for Deep Research Agents
by: Rasheed, Razeen A, et al.
Published: (2026)

Duplicate Question Retrieval and Confirmation Time Prediction in Software Communities
by: Hazra, Rima, et al.
Published: (2023)

Tutoring Large Language Models to be Domain-adaptive, Precise, and Safe
by: Banerjee, Somnath
Published: (2026)

Towards Safer Pretraining: Analyzing and Filtering Harmful Content in Webscale datasets for Responsible LLMs
by: Mendu, Sai Krishna, et al.
Published: (2025)

Socio-Culturally Aware Evaluation Framework for LLM-Based Content Moderation
by: Kumar, Shanu, et al.
Published: (2024)

InfFeed: Influence Functions as a Feedback to Improve the Performance of Subjective Tasks
by: Banerjee, Somnath, et al.
Published: (2024)

SCULPT: Systematic Tuning of Long Prompts
by: Kumar, Shanu, et al.
Published: (2024)

TEXT2AFFORD: Probing Object Affordance Prediction abilities of Language Models solely from Text
by: Adak, Sayantan, et al.
Published: (2024)

Enhancing Zero-shot Chain of Thought Prompting via Uncertainty-Guided Strategy Selection
by: Kumar, Shanu, et al.
Published: (2024)

Turning Logic Against Itself : Probing Model Defenses Through Contrastive Questions
by: Sachdeva, Rachneet, et al.
Published: (2025)

Analyzing Sentiment Polarity Reduction in News Presentation through Contextual Perturbation and Large Language Models
by: Kuila, Alapan, et al.
Published: (2024)

Noiser: Bounded Input Perturbations for Attributing Large Language Models
by: Madani, Mohammad Reza Ghasemi, et al.
Published: (2025)

Benchmarking Motivational Interviewing Competence of Large Language Models
by: Jha, Aishwariya, et al.
Published: (2026)

Integrating Large Language Models with Graph-based Reasoning for Conversational Question Answering
by: Jain, Parag, et al.
Published: (2024)

When Choices Become Risks: Safety Failures of Large Language Models under Multiple-Choice Constraints
by: Chen, Yuheng, et al.
Published: (2026)

Talent or Luck? Evaluating Attribution Bias in Large Language Models
by: Raj, Chahat, et al.
Published: (2025)

Named Entity Recognition on Code-Mixed Cross-Script Social Media Content
by: Somnath Banerjee
Published: (2017)

Diagnosing Failures in Large Language Models' Answers: Integrating Error Attribution into Evaluation Framework
by: Xu, Zishan, et al.
Published: (2025)

On Zero-Shot Counterspeech Generation by LLMs
by: Saha, Punyajoy, et al.
Published: (2024)

READ: Reinforcement-based Adversarial Learning for Text Classification with Limited Labeled Data
by: Sharma, Rohit, et al.
Published: (2025)

CodeMixBench: Evaluating Large Language Models on Code Generation with Code-Mixed Prompts
by: Sheokand, Manik, et al.
Published: (2025)

Exploring Safety-Utility Trade-Offs in Personalized Language Models
by: Vijjini, Anvesh Rao, et al.
Published: (2024)