Image de couverture de livre

Beyond Perplexity: Multi-dimensional Safety Evaluation of LLM Compression

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Xu, Zhichao, Gupta, Ashim, Li, Tao, Bentham, Oliver, Srikumar, Vivek
Format:	Preprint
Publié:	2024
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Found in Translation: Measuring Multilingual LLM Consistency as Simple as Translate then Evaluate
par: Gupta, Ashim, et autres
Publié: (2025)

InfiniteScienceGym: An Unbounded, Procedurally-Generated Benchmark for Scientific Analysis
par: Bentham, Oliver, et autres
Publié: (2026)

Test-Time Scaling with Repeated Sampling Improves Multilingual Text Generation
par: Gupta, Ashim, et autres
Publié: (2025)

State Space Models are Strong Text Rerankers
par: Xu, Zhichao, et autres
Publié: (2024)

Defragmenting Language Models: An Interpretability-based Approach for Vocabulary Expansion
par: Mehta, Maitrey, et autres
Publié: (2026)

An Empirical Investigation of Matrix Factorization Methods for Pre-trained Transformers
par: Gupta, Ashim, et autres
Publié: (2024)

Whispers of Doubt Amidst Echoes of Triumph in NLP Robustness
par: Gupta, Ashim, et autres
Publié: (2023)

In-Context Example Ordering Guided by Label Distributions
par: Xu, Zhichao, et autres
Publié: (2024)

LLM-Symbolic Integration for Robust Temporal Tabular Reasoning
par: Kulkarni, Atharv, et autres
Publié: (2025)

Unequal Voices: How LLMs Construct Constrained Queer Narratives
par: Ghosal, Atreya, et autres
Publié: (2025)

Distillation versus Contrastive Learning: How to Train Your Rerankers
par: Xu, Zhichao, et autres
Publié: (2025)

Multi-dimensional Evaluation of Empathetic Dialog Responses
par: Xu, Zhichao, et autres
Publié: (2024)

Reinforcing Code Generation: Improving Text-to-SQL with Execution-Based Learning
par: Kulkarni, Atharv, et autres
Publié: (2025)

Understanding the Logic of Direct Preference Alignment through Logic
par: Richardson, Kyle, et autres
Publié: (2024)

Promptly Predicting Structures: The Return of Inference
par: Mehta, Maitrey, et autres
Publié: (2024)

Enhancing Question Answering on Charts Through Effective Pre-training Tasks
par: Gupta, Ashim, et autres
Publié: (2024)

Rethinking Perplexity: Revealing the Impact of Input Length on Perplexity Evaluation in LLMs
par: Cheng, Letian, et autres
Publié: (2026)

Chain-of-Thought Unfaithfulness as Disguised Accuracy
par: Bentham, Oliver, et autres
Publié: (2024)

The Perplexity Paradox: Why Code Compresses Better Than Math in LLM Prompts
par: Johnson, Warren
Publié: (2026)

Perplexed by Perplexity: Perplexity-Based Data Pruning With Small Reference Models
par: Ankner, Zachary, et autres
Publié: (2024)

LACONIC: Dense-Level Effectiveness for Scalable Sparse Retrieval via a Two-Phase Training Curriculum
par: Xu, Zhichao, et autres
Publié: (2026)

Rethinking On-policy Optimization for Query Augmentation
par: Xu, Zhichao, et autres
Publié: (2025)

Beyond Perplexity: Character Distribution Signatures and the MDTA Benchmark for AI Text Detection
par: Narayanasamy, Priyadarshan, et autres
Publié: (2026)

JudgeAgent: Beyond Static Benchmarks for Knowledge-Driven and Dynamic LLM Evaluation
par: Shi, Zhichao, et autres
Publié: (2025)

Multi-Lingual Cyber Threat Detection in Tweets/X Using ML, DL, and LLM: A Comparative Analysis
par: Murad, Saydul Akbar, et autres
Publié: (2025)

Beyond Natural Language Perplexity: Detecting Dead Code Poisoning in Code Generation Datasets
par: Tsai, Chi-Chien, et autres
Publié: (2025)

Beyond Perplexity: Let the Reader Select Retrieval Summaries via Spectrum Projection Score
par: Hu, Zhanghao, et autres
Publié: (2025)

Perplexity Trap: PLM-Based Retrievers Overrate Low Perplexity Documents
par: Wang, Haoyu, et autres
Publié: (2025)

Low-Perplexity LLM-Generated Sequences and Where To Find Them
par: Wuhrmann, Arthur, et autres
Publié: (2025)

Mitigating Forgetting in LLM Fine-Tuning via Low-Perplexity Token Learning
par: Wu, Chao-Chung, et autres
Publié: (2025)

RLShield: Practical Multi-Agent RL for Financial Cyber Defense with Attack-Surface MDPs and Real-Time Response Orchestration
par: Nayak, Srikumar
Publié: (2026)

Beyond English and Evasion: A Human-Annotated Multi-Domain Benchmark for High-Stakes LLM Safety Evaluation in Chinese
par: Zaghouani, Wajdi, et autres
Publié: (2026)

Beyond Perplexity: A Lightweight Benchmark for Knowledge Retention in Supervised Fine-Tuning
par: Shabgahi, Soheil Zibakhsh, et autres
Publié: (2026)

On the Fallacy of Global Token Perplexity in Spoken Language Model Evaluation
par: Hsu, Chan-Jan, et autres
Publié: (2026)

Beyond One-Size-Fits-All: Multi-Domain, Multi-Task Framework for Embedding Model Selection
par: Khetan, Vivek
Publié: (2024)

Can Perplexity Reflect Large Language Model's Ability in Long Text Understanding?
par: Hu, Yutong, et autres
Publié: (2024)

The Hidden Dimensions of LLM Alignment: A Multi-Dimensional Analysis of Orthogonal Safety Directions
par: Pan, Wenbo, et autres
Publié: (2025)

Rectify Evaluation Preference: Improving LLMs' Critique on Math Reasoning via Perplexity-aware Reinforcement Learning
par: Tian, Changyuan, et autres
Publié: (2025)

PatentScore: Multi-dimensional Evaluation of LLM-Generated Patent Claims
par: Yoo, Yongmin, et autres
Publié: (2025)

A Perplexity and Menger Curvature-Based Approach for Similarity Evaluation of Large Language Models
par: Zhang, Yuantao, et autres
Publié: (2025)