Copertina

Exposing Long-Tail Safety Failures in Large Language Models through Efficient Diverse Response Sampling

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Hajra, Suvadeep, Nandi, Palash, Chakraborty, Tanmoy
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Innocence in the Crossfire: Roles of Skip Connections in Jailbreaking Visual Language Models
di: Nandi, Palash, et al.
Pubblicazione: (2025)

SABER: Uncovering Vulnerabilities in Safety Alignment via Cross-Layer Residual Connection
di: Joshi, Maithili, et al.
Pubblicazione: (2025)

SAFE-MEME: Structured Reasoning Framework for Robust Hate Speech Detection in Memes
di: Nandi, Palash, et al.
Pubblicazione: (2024)

Recent Advances in Hate Speech Moderation: Multimodality and the Role of Large Models
di: Hee, Ming Shan, et al.
Pubblicazione: (2024)

First Finish Search: Efficient Test-Time Scaling in Large Language Models
di: Agarwal, Aradhye, et al.
Pubblicazione: (2025)

Markovian ODE-guided scoring can assess the quality of offline reasoning traces in language models
di: Nandi, Arghodeep, et al.
Pubblicazione: (2026)

Information Anxiety in Large Language Models
di: Bajpai, Prasoon, et al.
Pubblicazione: (2024)

Compression Laws for Large Language Models
di: Sengupta, Ayan, et al.
Pubblicazione: (2025)

Short-Range Dependency Effects on Transformer Instability and a Decomposed Attention Solution
di: Hajra, Suvadeep
Pubblicazione: (2025)

Step-by-Step Unmasking for Parameter-Efficient Fine-tuning of Large Language Models
di: Agarwal, Aradhye, et al.
Pubblicazione: (2024)

The Art of Scaling Test-Time Compute for Large Language Models
di: Agarwal, Aradhye, et al.
Pubblicazione: (2025)

Multilingual Needle in a Haystack: Investigating Long-Context Behavior of Multilingual Large Language Models
di: Hengle, Amey, et al.
Pubblicazione: (2024)

Harmonizing Code-mixed Conversations: Personality-assisted Code-mixed Response Generation in Dialogues
di: Kumar, Shivani, et al.
Pubblicazione: (2024)

Listening Between the Lines: Decoding Podcast Narratives with Language Modeling
di: Gupta, Shreya, et al.
Pubblicazione: (2025)

Temporally Consistent Factuality Probing for Large Language Models
di: Bajpai, Ashutosh, et al.
Pubblicazione: (2024)

Knowledge Planning in Large Language Models for Domain-Aligned Counseling Summarization
di: Srivastava, Aseem, et al.
Pubblicazione: (2024)

FLAME: Self-Supervised Low-Resource Taxonomy Expansion using Large Language Models
di: Mishra, Sahil, et al.
Pubblicazione: (2024)

MULTIVERSE: Exposing Large Language Model Alignment Problems in Diverse Worlds
di: Jin, Xiaolong, et al.
Pubblicazione: (2024)

Post-training Large Language Models for Diverse High-Quality Responses
di: Chen, Yilei, et al.
Pubblicazione: (2025)

From Images to Words: Efficient Cross-Modal Knowledge Distillation to Language Models from Black-box Teachers
di: Sengupta, Ayan, et al.
Pubblicazione: (2026)

Mechanistic Behavior Editing of Language Models
di: Singh, Joykirat, et al.
Pubblicazione: (2024)

Decoding Memes: Benchmarking Narrative Role Classification across Multilingual and Multimodal Models
di: Sharma, Shivam, et al.
Pubblicazione: (2025)

Understanding the Physics of Key-Value Cache Compression for LLMs through Attention Dynamics
di: Ananthanarayanan, Samhruth, et al.
Pubblicazione: (2026)

HIDE and Seek: Detecting Hallucinations in Language Models via Decoupled Representations
di: Chatterjee, Anwoy, et al.
Pubblicazione: (2025)

Counterspeech the ultimate shield! Multi-Conditioned Counterspeech Generation through Attributed Prefix Learning
di: Kumar, Aswini, et al.
Pubblicazione: (2025)

coTherapist: A Behavior-Aligned Small Language Model to Support Mental Healthcare Experts
di: Adhikary, Prottay Kumar, et al.
Pubblicazione: (2026)

LongSafety: Evaluating Long-Context Safety of Large Language Models
di: Lu, Yida, et al.
Pubblicazione: (2025)

$\texttt{LM}^\texttt{2}$: A Simple Society of Language Models Solves Complex Reasoning
di: Juneja, Gurusha, et al.
Pubblicazione: (2024)

Persona-aware Generative Model for Code-mixed Language
di: Sengupta, Ayan, et al.
Pubblicazione: (2023)

Language Models can Exploit Cross-Task In-context Learning for Data-Scarce Novel Tasks
di: Chatterjee, Anwoy, et al.
Pubblicazione: (2024)

Long-Tail Crisis in Nearest Neighbor Language Models
di: Nishida, Yuto, et al.
Pubblicazione: (2025)

Multilingual Test-Time Scaling via Initial Thought Transfer
di: Bajpai, Prasoon, et al.
Pubblicazione: (2025)

Data Advisor: Dynamic Data Curation for Safety Alignment of Large Language Models
di: Wang, Fei, et al.
Pubblicazione: (2024)

Long-Tail Knowledge in Large Language Models: Taxonomy, Mechanisms, Interventions and Implications
di: Badhe, Sanket, et al.
Pubblicazione: (2026)

Self-Evolved Preference Optimization for Enhancing Mathematical Reasoning in Small Language Models
di: Singh, Joykirat, et al.
Pubblicazione: (2025)

POSIX: A Prompt Sensitivity Index For Large Language Models
di: Chatterjee, Anwoy, et al.
Pubblicazione: (2024)

Multilingual LLMs Inherently Reward In-Language Time-Sensitive Semantic Alignment for Low-Resource Languages
di: Bajpai, Ashutosh, et al.
Pubblicazione: (2024)

You Only Prune Once: Designing Calibration-Free Model Compression With Policy Learning
di: Sengupta, Ayan, et al.
Pubblicazione: (2025)

Latent Performance Profiling of Large Language Models
di: Chakraborty, Tanmoy, et al.
Pubblicazione: (2026)

TrackList: Tracing Back Query Linguistic Diversity for Head and Tail Knowledge in Open Large Language Models
di: Buhnila, Ioana, et al.
Pubblicazione: (2025)