Imagen de Portada

More of the Same: Persistent Representational Harms Under Increased Representation

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Mickel, Jennifer, De-Arteaga, Maria, Liu, Leqi, Tian, Kevin
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Beyond Behaviorist Representational Harms: A Plan for Measurement and Mitigation
por: Chien, Jennifer, et al.
Publicado: (2024)

Linear Representation Transferability Hypothesis: Leveraging Small Models to Steer Large Models
por: Bello, Femi, et al.
Publicado: (2025)

Racial/Ethnic Categories in AI and Algorithmic Fairness: Why They Matter and What They Represent
por: Mickel, Jennifer
Publicado: (2024)

More Women, Same Stereotypes: Unpacking the Gender Bias Paradox in Large Language Models
por: Chen, Evan, et al.
Publicado: (2025)

Same Task, More Tokens: the Impact of Input Length on the Reasoning Performance of Large Language Models
por: Levy, Mosh, et al.
Publicado: (2024)

Latent Fusion Jailbreak: Blending Harmful and Harmless Representations to Elicit Unsafe LLM Outputs
por: Xing, Wenpeng, et al.
Publicado: (2025)

Teaching with Lies: Curriculum DPO on Synthetic Negatives for Hallucination Detection
por: Pandit, Shrey, et al.
Publicado: (2025)

Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs
por: Sheshadri, Abhay, et al.
Publicado: (2024)

More Agents Improve Math Problem Solving but Adversarial Robustness Gap Persists
por: Alavi, Khashayar, et al.
Publicado: (2025)

Booster: Tackling Harmful Fine-tuning for Large Language Models via Attenuating Harmful Perturbation
por: Huang, Tiansheng, et al.
Publicado: (2024)

Learning Composable Chains-of-Thought
por: Yin, Fangcong, et al.
Publicado: (2025)

Filtered Reasoning Score: Evaluating Reasoning Quality on a Model's Most-Confident Traces
por: Pathak, Manas, et al.
Publicado: (2026)

Is This Just Fantasy? Language Model Representations Reflect Human Judgments of Event Plausibility
por: Lepori, Michael A., et al.
Publicado: (2025)

HarmMetric Eval: Benchmarking Metrics and Judges for LLM Harmfulness Assessment
por: Yang, Langqi, et al.
Publicado: (2025)

Self-HarmLLM: Can Large Language Model Harm Itself?
por: Kim, Heehwan, et al.
Publicado: (2025)

The Representational Geometry of Number
por: Hu, Zhimin, et al.
Publicado: (2026)

Harm or Humor: A Multimodal, Multilingual Benchmark for Overt and Covert Harmful Humor
por: Sharshar, Ahmed, et al.
Publicado: (2026)

Language-Independent Representations Improve Zero-Shot Summarization
por: Solovyev, Vladimir, et al.
Publicado: (2024)

Less is More: Resource-Efficient Low-Rank Adaptation
por: Tian, Chunlin, et al.
Publicado: (2025)

mOthello: When Do Cross-Lingual Representation Alignment and Cross-Lingual Transfer Emerge in Multilingual Models?
por: Hua, Tianze, et al.
Publicado: (2024)

HarmTransform: Transforming Explicit Harmful Queries into Stealthy via Multi-Agent Debate
por: Zhu, Shenzhe
Publicado: (2025)

Mechanistic Decomposition of Sentence Representations
por: Tehenan, Matthieu, et al.
Publicado: (2025)

Localizing Persona Representations in LLMs
por: Cintas, Celia, et al.
Publicado: (2025)

The Presupposition Problem in Representation Genesis
por: Wu, Yiling
Publicado: (2026)

Sense Representations Are Inducible Interfaces
por: Cruz, Jan Christian Blaise, et al.
Publicado: (2026)

Investigating Idiomaticity in Word Representations
por: He, Wei, et al.
Publicado: (2024)

Efficient Information Extraction in Few-Shot Relation Classification through Contrastive Representation Learning
por: Borchert, Philipp, et al.
Publicado: (2024)

Vector-ICL: In-context Learning with Continuous Vector Representations
por: Zhuang, Yufan, et al.
Publicado: (2024)

Automated Triaging and Transfer Learning of Incident Learning Safety Reports Using Large Language Representational Models
por: Beidler, Peter, et al.
Publicado: (2025)

PluriHarms: Benchmarking the Full Spectrum of Human Judgments on AI Harm
por: Li, Jing-Jing, et al.
Publicado: (2026)

`For Argument's Sake, Show Me How to Harm Myself!': Jailbreaking LLMs in Suicide and Self-Harm Contexts
por: Schoene, Annika M, et al.
Publicado: (2025)

LLM-Agnostic Semantic Representation Attack
por: Lian, Jiawei, et al.
Publicado: (2026)

Middle-Layer Representation Alignment for Cross-Lingual Transfer in Fine-Tuned LLMs
por: Liu, Danni, et al.
Publicado: (2025)

REACT: Representation Extraction And Controllable Tuning to Overcome Overfitting in LLM Knowledge Editing
por: Zhong, Haitian, et al.
Publicado: (2025)

Diversifying the Mixture-of-Experts Representation for Language Models with Orthogonal Optimizer
por: Liu, Boan, et al.
Publicado: (2023)

Learning Granularity Representation for Temporal Knowledge Graph Completion
por: Zhang, Jinchuan, et al.
Publicado: (2024)

IsoBench: Benchmarking Multimodal Foundation Models on Isomorphic Representations
por: Fu, Deqing, et al.
Publicado: (2024)

Personalized Language Modeling from Personalized Human Feedback
por: Li, Xinyu, et al.
Publicado: (2024)

Active Use of Latent Constituency Representation in both Humans and Large Language Models
por: Liu, Wei, et al.
Publicado: (2024)

EmbeddingGemma: Powerful and Lightweight Text Representations
por: Vera, Henrique Schechter, et al.
Publicado: (2025)