Cover Image

Inference-Time Toxicity Mitigation in Protein Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Burda, Manuel Fernández, Aranguri, Santiago, Moreno, Iván Arcuschin, Ferrante, Enzo
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Probe-Based Data Attribution: Discovering and Mitigating Undesirable Behaviors in LLM Post-Training
by: Xiao, Frank, et al.
Published: (2026)

Mixed Dynamics In Linear Networks: Unifying the Lazy and Active Regimes
by: Tu, Zhenfeng, et al.
Published: (2024)

Automatically Finding Reward Model Biases
by: Wang, Atticus, et al.
Published: (2026)

Understanding Reasoning in Thinking Language Models via Steering Vectors
by: Venhoff, Constantin, et al.
Published: (2025)

Base Models Know How to Reason, Thinking Models Learn When
by: Venhoff, Constantin, et al.
Published: (2025)

Biases in the Blind Spot: Detecting What LLMs Fail to Mention
by: Arcuschin, Iván, et al.
Published: (2026)

Measuring Chain-of-Thought Monitorability Through Faithfulness and Verbosity
by: Meek, Austin, et al.
Published: (2025)

Chain-of-Thought Reasoning In The Wild Is Not Always Faithful
by: Arcuschin, Iván, et al.
Published: (2025)

Mitigating Over-Refusal in Aligned Large Language Models via Inference-Time Activation Energy
by: Jiang, Eric Hanchen, et al.
Published: (2025)

Phase-aware Training Schedule Simplifies Learning in Flow-Based Generative Models
by: Aranguri, Santiago, et al.
Published: (2024)

Preference Tuning For Toxicity Mitigation Generalizes Across Languages
by: Li, Xiaochen, et al.
Published: (2024)

How Culturally Aware are Vision-Language Models?
by: Burda-Lassen, Olena, et al.
Published: (2024)

Scalable Simulation-Based Model Inference with Test-Time Complexity Control
by: Gloeckler, Manuel, et al.
Published: (2026)

Structure-Aligned Protein Language Model
by: Chen, Can, et al.
Published: (2025)

RosettaSearch: Multi-Objective Inference-Time Search for Protein Sequence Design
by: Kshirsagar, Meghana, et al.
Published: (2026)

Exploring Large Protein Language Models in Constrained Evaluation Scenarios within the FLIP Benchmark
by: Mollon, Manuel F., et al.
Published: (2025)

Remedying uncertainty representations in visual inference through Explaining-Away Variational Autoencoders
by: Catoni, Josefina, et al.
Published: (2024)

Protein Language Models Diverge from Natural Language: Comparative Analysis and Improved Inference
by: Hart, Anna, et al.
Published: (2026)

Apollo-Forecast: Overcoming Aliasing and Inference Speed Challenges in Language Models for Time Series Forecasting
by: Yin, Tianyi, et al.
Published: (2024)

Transforming Multimodal Models into Action Models for Radiotherapy
by: Ferrante, Matteo, et al.
Published: (2025)

Temper and Tilt Lead to SLOP: Reward Hacking Mitigation with Inference-Time Alignment
by: Wang, Ye, et al.
Published: (2026)

Mitigating Premature Exploitation in Particle-based Monte Carlo for Inference-Time Scaling
by: Giannone, Giorgio, et al.
Published: (2025)

Flash Inference: Near Linear Time Inference for Long Convolution Sequence Models and Beyond
by: Oncescu, Costin-Andrei, et al.
Published: (2024)

Model-Distributed Inference for Large Language Models at the Edge
by: Macario, Davide, et al.
Published: (2025)

Diversified Scaling Inference in Time Series Foundation Models
by: Hua, Ruijin, et al.
Published: (2026)

Dynamic Search for Inference-Time Alignment in Diffusion Models
by: Li, Xiner, et al.
Published: (2025)

Membership Inference Attacks Against Time-Series Models
by: Koren, Noam, et al.
Published: (2024)

Fast Inference for Augmented Large Language Models
by: Shahout, Rana, et al.
Published: (2024)

ILRR: Inference-Time Steering Method for Masked Diffusion Language Models
by: Avrahami, Eden, et al.
Published: (2026)

Mitigating Memorization In Language Models
by: Sakarvadia, Mansi, et al.
Published: (2024)

Inference-Time Alignment of Diffusion Models with Direct Noise Optimization
by: Tang, Zhiwei, et al.
Published: (2024)

Membership Inference Attacks on Discrete Diffusion Language Models
by: Kasivelrajan, Shailesh
Published: (2026)

Context-Selective State Space Models: Feedback is All You Need
by: Zattra, Riccardo, et al.
Published: (2025)

Ever: Mitigating Hallucination in Large Language Models through Real-Time Verification and Rectification
by: Kang, Haoqiang, et al.
Published: (2023)

Toward Safer Diffusion Language Models: Discovery and Mitigation of Priming Vulnerability
by: Yamabe, Shojiro, et al.
Published: (2025)

Inference Time Debiasing Concepts in Diffusion Models
by: Kupssinskü, Lucas S., et al.
Published: (2025)

AdaMixup: A Dynamic Defense Framework for Membership Inference Attack Mitigation
by: Chen, Ying, et al.
Published: (2025)

Inference-Time Scaling in Diffusion Models through Iterative Partial Refinement
by: Kang, Taegu, et al.
Published: (2026)

Inference-Time Intervention: Eliciting Truthful Answers from a Language Model
by: Li, Kenneth, et al.
Published: (2023)

Inference-Time Alignment Control for Diffusion Models with Reinforcement Learning Guidance
by: Jin, Luozhijie, et al.
Published: (2025)