Copertina

Lottery Ticket Adaptation: Mitigating Destructive Interference in LLMs

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Panda, Ashwinee, Isik, Berivan, Qi, Xiangyu, Koyejo, Sanmi, Weissman, Tsachy, Mittal, Prateek
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Computation and Language Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

On Fairness of Low-Rank Adaptation of Large Models
di: Ding, Zhoujie, et al.
Pubblicazione: (2024)

Teach LLMs to Phish: Stealing Private Information from Language Models
di: Panda, Ashwinee, et al.
Pubblicazione: (2024)

LoRI: Reducing Cross-Task Interference in Multi-Task Low-Rank Adaptation
di: Zhang, Juzheng, et al.
Pubblicazione: (2025)

Adaptive Compression in Federated Learning via Side Information
di: Isik, Berivan, et al.
Pubblicazione: (2023)

KS-Lottery: Finding Certified Lottery Tickets for Multilingual Language Models
di: Yuan, Fei, et al.
Pubblicazione: (2024)

The Inadequacy of Offline LLM Evaluations: A Need to Account for Personalization in Model Behavior
di: Wang, Angelina, et al.
Pubblicazione: (2025)

GaussianVision: Vision-Language Alignment from Compressed Image Representations using 2D Gaussian Splatting
di: Omri, Yasmine, et al.
Pubblicazione: (2025)

HEART: A Unified Benchmark for Assessing Humans and LLMs in Emotional Support Dialogue
di: Iyer, Laya, et al.
Pubblicazione: (2026)

Scaling Laws for Downstream Task Performance of Large Language Models
di: Isik, Berivan, et al.
Pubblicazione: (2024)

Why Do Safety Guardrails Degrade Across Languages?
di: Zhang, Max, et al.
Pubblicazione: (2026)

Logits are All We Need to Adapt Closed Models
di: Hiranandani, Gaurush, et al.
Pubblicazione: (2025)

Extracting books from production language models
di: Ahmed, Ahmed, et al.
Pubblicazione: (2026)

Differentially Private Adaptation of Diffusion Models via Noisy Aggregated Embeddings
di: Peetathawatchai, Pura, et al.
Pubblicazione: (2024)

Alignment-Constrained Dynamic Pruning for LLMs: Identifying and Preserving Alignment-Critical Circuits
di: Patel, Dev, et al.
Pubblicazione: (2025)

Reliable and Efficient Amortized Model-based Evaluation
di: Truong, Sang, et al.
Pubblicazione: (2025)

A New Linear Scaling Rule for Private Adaptive Hyperparameter Optimization
di: Panda, Ashwinee, et al.
Pubblicazione: (2022)

Safety Alignment Should Be Made More Than Just a Few Tokens Deep
di: Qi, Xiangyu, et al.
Pubblicazione: (2024)

Private Fine-tuning of Large Language Models with Zeroth-order Optimization
di: Tang, Xinyu, et al.
Pubblicazione: (2024)

From Passive to Active Reasoning: Can Large Language Models Ask the Right Questions under Incomplete Information?
di: Zhou, Zhanke, et al.
Pubblicazione: (2025)

The Model Hears You: Audio Language Model Deployments Should Consider the Principle of Least Privilege
di: He, Luxi, et al.
Pubblicazione: (2025)

In-Situ Behavioral Evaluation for LLM Fairness, Not Standardized-Test Scores
di: Tang, Zeyu, et al.
Pubblicazione: (2026)

CURE: Cultural Understanding and Reasoning Evaluation - A Framework for "Thick" Culture Alignment Evaluation in LLMs
di: Vo, Truong, et al.
Pubblicazione: (2025)

Lean-ing on Quality: How High-Quality Data Beats Diverse Multilingual Data in AutoFormalization
di: Chan, Willy, et al.
Pubblicazione: (2025)

Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications
di: Wei, Boyi, et al.
Pubblicazione: (2024)

Mitigating Catastrophic Forgetting in Target Language Adaptation of LLMs via Source-Shielded Updates
di: Yamaguchi, Atsuki, et al.
Pubblicazione: (2025)

On the Sparsity of the Strong Lottery Ticket Hypothesis
di: Natale, Emanuele, et al.
Pubblicazione: (2024)

SATBench: Benchmarking LLMs' Logical Reasoning via Automated Puzzle Generation from SAT Formulas
di: Wei, Anjiang, et al.
Pubblicazione: (2025)

ZIP-FIT: Embedding-Free Data Selection via Compression-Based Alignment
di: Obbad, Elyas, et al.
Pubblicazione: (2024)

Quantifying the Importance of Data Alignment in Downstream Model Performance
di: Chawla, Krrish, et al.
Pubblicazione: (2025)

Is Pre-training Truly Better Than Meta-Learning?
di: Miranda, Brando, et al.
Pubblicazione: (2023)

Uncovering Critical Features for Deepfake Detection through the Lottery Ticket Hypothesis
di: Amin, Lisan Al, et al.
Pubblicazione: (2025)

Adding Chocolate to Mint: Mitigating Metric Interference in Machine Translation
di: Pombal, José, et al.
Pubblicazione: (2025)

Investigating Data Contamination for Pre-training Language Models
di: Jiang, Minhao, et al.
Pubblicazione: (2024)

Do LLMs Follow Their Own Rules? A Reflexive Audit of Self-Stated Safety Policies
di: Mittal, Avni
Pubblicazione: (2026)

Privacy Auditing of Large Language Models
di: Panda, Ashwinee, et al.
Pubblicazione: (2025)

Mind the Confidence Gap: Overconfidence, Calibration, and Distractor Effects in Large Language Models
di: Chhikara, Prateek
Pubblicazione: (2025)

The Sound of Syntax: Finetuning and Comprehensive Evaluation of Language Models for Speech Pathology
di: Patel, Fagun, et al.
Pubblicazione: (2025)

Beyond Scale: The Diversity Coefficient as a Data Quality Metric for Variability in Natural Language Data
di: Miranda, Brando, et al.
Pubblicazione: (2023)

Does Safety Training of LLMs Generalize to Semantically Related Natural Prompts?
di: Addepalli, Sravanti, et al.
Pubblicazione: (2024)

LOTUS: Improving Transformer Efficiency with Sparsity Pruning and Data Lottery Tickets
di: Upadhyay, Ojasw
Pubblicazione: (2024)