Copertina

LLM Targeted Underperformance Disproportionately Impacts Vulnerable Users

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Poole-Dayan, Elinor, Roy, Deb, Kabbara, Jad
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Computation and Language Artificial Intelligence Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

An AI-Powered Framework for Analyzing Collective Idea Evolution in Deliberative Assemblies
di: Poole-Dayan, Elinor, et al.
Pubblicazione: (2025)

On the Relationship between Truth and Political Bias in Language Models
di: Fulay, Suyash, et al.
Pubblicazione: (2024)

Computational Analysis of Conversation Dynamics through Participant Responsivity
di: Hughes, Margaret, et al.
Pubblicazione: (2025)

Confidence Under the Hood: An Investigation into the Confidence-Probability Alignment in Large Language Models
di: Kumar, Abhishek, et al.
Pubblicazione: (2024)

PersonaLLM: Investigating the Ability of Large Language Models to Express Personality Traits
di: Jiang, Hang, et al.
Pubblicazione: (2023)

Bridging Context Gaps: Enhancing Comprehension in Long-Form Social Conversations Through Contextualized Excerpts
di: Mohanty, Shrestha, et al.
Pubblicazione: (2024)

AI Sandbagging: Language Models can Strategically Underperform on Evaluations
di: van der Weij, Teun, et al.
Pubblicazione: (2024)

User-LLM: Efficient LLM Contextualization with User Embeddings
di: Ning, Lin, et al.
Pubblicazione: (2024)

On the Limitations of Language Targeted Pruning: Investigating the Calibration Language Impact in Multilingual LLM Pruning
di: Kurz, Simon, et al.
Pubblicazione: (2024)

SocialHarmBench: Revealing LLM Vulnerabilities to Socially Harmful Requests
di: Pandey, Punya Syon, et al.
Pubblicazione: (2025)

RLTHF: Targeted Human Feedback for LLM Alignment
di: Xu, Yifei, et al.
Pubblicazione: (2025)

LLM See, LLM Do: Guiding Data Generation to Target Non-Differentiable Objectives
di: Shimabucoro, Luísa, et al.
Pubblicazione: (2024)

LLMAP: LLM-Assisted Multi-Objective Route Planning with User Preferences
di: Yuan, Liangqi, et al.
Pubblicazione: (2025)

From Exact Hits to Close Enough: Semantic Caching for LLM Embeddings
di: Biton, Dvir David, et al.
Pubblicazione: (2026)

The Impact of Language Mixing on Bilingual LLM Reasoning
di: Li, Yihao, et al.
Pubblicazione: (2025)

Transparent Screening for LLM Inference and Training Impacts
di: Pachot, Arnault, et al.
Pubblicazione: (2026)

Building, Reusing, and Generalizing Abstract Representations from Concrete Sequences
di: Wu, Shuchen, et al.
Pubblicazione: (2024)

Factual Inconsistency in Data-to-Text Generation Scales Exponentially with LLM Size: A Statistical Validation
di: Mahapatra, Joy, et al.
Pubblicazione: (2025)

GanitLLM: Difficulty-Aware Bengali Mathematical Reasoning through Curriculum-GRPO
di: Dipta, Shubhashis Roy, et al.
Pubblicazione: (2026)

Systematically Analyzing Prompt Injection Vulnerabilities in Diverse LLM Architectures
di: Benjamin, Victoria, et al.
Pubblicazione: (2024)

Are My Optimized Prompts Compromised? Exploring Vulnerabilities of LLM-based Optimizers
di: Zhao, Andrew, et al.
Pubblicazione: (2025)

When Greedy Wins: Emergent Exploitation Bias in Meta-Bandit LLM Training
di: Chen, Sanxing, et al.
Pubblicazione: (2025)

JuStRank: Benchmarking LLM Judges for System Ranking
di: Gera, Ariel, et al.
Pubblicazione: (2024)

CLEAR: Error Analysis via LLM-as-a-Judge Made Easy
di: Yehudai, Asaf, et al.
Pubblicazione: (2025)

Survey on Evaluation of LLM-based Agents
di: Yehudai, Asaf, et al.
Pubblicazione: (2025)

HindSight: Evaluating LLM-Generated Research Ideas via Future Impact
di: Jiang, Bo
Pubblicazione: (2026)

Breach in the Shield: Unveiling the Vulnerabilities of Large Language Models
di: Dai, Runpeng, et al.
Pubblicazione: (2025)

UserBench: An Interactive Gym Environment for User-Centric Agents
di: Qian, Cheng, et al.
Pubblicazione: (2025)

In Vino Veritas and Vulnerabilities: Examining LLM Safety via Drunk Language Inducement
di: Shetty, Anudeex, et al.
Pubblicazione: (2026)

Stay Tuned: An Empirical Study of the Impact of Hyperparameters on LLM Tuning in Real-World Applications
di: Halfon, Alon, et al.
Pubblicazione: (2024)

Accidental Vulnerability: Factors in Fine-Tuning that Shift Model Safeguards
di: Pandey, Punya Syon, et al.
Pubblicazione: (2025)

To Think or Not to Think: Exploring the Unthinking Vulnerability in Large Reasoning Models
di: Zhu, Zihao, et al.
Pubblicazione: (2025)

Vulnerability Mitigation for Safety-Aligned Language Models via Debiasing
di: Tran, Thien Q., et al.
Pubblicazione: (2025)

Controllable User Simulation
di: Tennenholtz, Guy, et al.
Pubblicazione: (2026)

UserSumBench: A Benchmark Framework for Evaluating User Summarization Approaches
di: Wang, Chao, et al.
Pubblicazione: (2024)

UserRL: Training Interactive User-Centric Agent via Reinforcement Learning
di: Qian, Cheng, et al.
Pubblicazione: (2025)

Who Gets Which Message? Auditing Demographic Bias in LLM-Generated Targeted Text
di: Islam, Tunazzina
Pubblicazione: (2026)

Advancing Jailbreak Strategies: A Hybrid Approach to Exploiting LLM Vulnerabilities and Bypassing Modern Defenses
di: Ahmed, Mohamed, et al.
Pubblicazione: (2025)

BiasJailbreak:Analyzing Ethical Biases and Jailbreak Vulnerabilities in Large Language Models
di: Lee, Isack, et al.
Pubblicazione: (2024)

Estimating LLM Consistency: A User Baseline vs Surrogate Metrics
di: Wu, Xiaoyuan, et al.
Pubblicazione: (2025)