Cover Image

Why Pass@k Optimization Can Degrade Pass@1: Prompt Interference in LLM Post-training

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Barakat, Anas, Chakraborty, Souradip, Pahwa, Khushbu, Bedi, Amrit Singh
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

On the Global Optimality of Policy Gradient Methods in General Utility Reinforcement Learning
by: Barakat, Anas, et al.
Published: (2024)

Align-Pro: A Principled Approach to Prompt Optimization for LLM Alignment
by: Trivedi, Prashant, et al.
Published: (2025)

Code Comprehension then Auditing for Unsupervised LLM Evaluation
by: Patel, Bhrij, et al.
Published: (2024)

PROPS: Progressively Private Self-alignment of Large Language Models
by: Teku, Noel, et al.
Published: (2025)

VARP: Reinforcement Learning from Vision-Language Model Feedback with Agent Regularized Preferences
by: Singh, Anukriti, et al.
Published: (2025)

Leveraging LLM Inconsistency to Boost Pass@k Performance
by: Dalal, Uri, et al.
Published: (2025)

RL with Learnable Textual Feedback: A Bilevel Approach
by: Singh, Utsav, et al.
Published: (2026)

MaxMin-RLHF: Alignment with Diverse Human Preferences
by: Chakraborty, Souradip, et al.
Published: (2024)

Test-Time Scaling in Diffusion LLMs via Hidden Semi-Autoregressive Experts
by: Lee, Jihoon, et al.
Published: (2025)

SAIL: Self-Improving Efficient Online Alignment of Large Language Models
by: Ding, Mucong, et al.
Published: (2024)

Multi-LLM QA with Embodied Exploration
by: Patel, Bhrij, et al.
Published: (2024)

RSPO: Risk-Seeking Policy Optimization for Pass@k and Max@k Metrics in Large Language Models
by: Zhang, Kaichen, et al.
Published: (2025)

Policy Gradients for Cumulative Prospect Theory in Reinforcement Learning
by: Lepel, Olivier, et al.
Published: (2024)

Policy Mirror Descent with Lookahead
by: Protopapas, Kimon, et al.
Published: (2024)

Achieving Zero Constraint Violation for Constrained Reinforcement Learning via Conservative Natural Policy Gradient Primal-Dual Algorithm
by: Bai, Qinbo, et al.
Published: (2022)

Immune: Improving Safety Against Jailbreaks in Multi-modal LLMs via Inference-Time Alignment
by: Ghosal, Soumya Suvra, et al.
Published: (2024)

Closing the Gap: Achieving Global Convergence (Last Iterate) of Actor-Critic under Markovian Sampling with Neural Network Parametrization
by: Gaur, Mudit, et al.
Published: (2024)

On The Sample Complexity Bounds In Bilevel Reinforcement Learning
by: Gaur, Mudit, et al.
Published: (2025)

Efficient Prediction of Pass@k Scaling in Large Language Models
by: Kazdan, Joshua, et al.
Published: (2025)

Beyond Text: Utilizing Vocal Cues to Improve Decision Making in LLMs for Robot Navigation Tasks
by: Sun, Xingpeng, et al.
Published: (2024)

Improved Sample Complexity For Diffusion Model Training Without Empirical Risk Minimizer Access
by: Gaur, Mudit, et al.
Published: (2025)

Draft-Conditioned Constrained Decoding for Structured Generation in LLMs
by: Reddy, Avinash, et al.
Published: (2026)

Graph Unitary Message Passing
by: Qiu, Haiquan, et al.
Published: (2024)

Uncertainty-Aware Answer Selection for Improved Reasoning in Multi-LLM Systems
by: Agrawal, Aakriti, et al.
Published: (2025)

Restoring the Sweet Spot: Pass-Rate Weighted Self-Distillation for LLM Reasoning
by: Liu, Zehao, et al.
Published: (2026)

Pass@k Training for Adaptively Balancing Exploration and Exploitation of Large Reasoning Models
by: Chen, Zhipeng, et al.
Published: (2025)

AdamS: Momentum Itself Can Be A Normalizer for LLM Pretraining and Post-training
by: Zhang, Huishuai, et al.
Published: (2025)

Brain alignment of reasoning and action representations from vision-language and action models during naturalistic gameplay
by: Oota, Subba Reddy, et al.
Published: (2026)

PassNet: Scaling Large Language Models for Graph Compiler Pass Generation
by: Liu, Yiqun, et al.
Published: (2026)

Active Preference Optimization for Sample Efficient RLHF
by: Das, Nirjhar, et al.
Published: (2024)

Enhancing LLM Agents for Code Generation with Possibility and Pass-rate Prioritized Experience Replay
by: Chen, Yuyang, et al.
Published: (2024)

Generative Modeling with Continuous Flows: Sample Complexity of Flow Matching
by: Gaur, Mudit, et al.
Published: (2025)

Improving Quantized Model Performance in Qualitative Analysis with Multi-Pass Prompt Verification
by: Adeseye, Aisvarya, et al.
Published: (2026)

Distributed Conformal Prediction via Message Passing
by: Wen, Haifeng, et al.
Published: (2025)

Neural-Symbolic Message Passing with Dynamic Pruning
by: Zhang, Chongzhi, et al.
Published: (2025)

Link Prediction with Untrained Message Passing Layers
by: Qarkaxhija, Lisi, et al.
Published: (2024)

DIPPER: Direct Preference Optimization to Accelerate Primitive-Enabled Hierarchical Reinforcement Learning
by: Singh, Utsav, et al.
Published: (2024)

REBEL: Reward Regularization-Based Approach for Robotic Reinforcement Learning from Human Feedback
by: Chakraborty, Souradip, et al.
Published: (2023)

Rethinking Adversarial Policies: A Generalized Attack Formulation and Provable Defense in RL
by: Liu, Xiangyu, et al.
Published: (2023)

Could Chemical LLMs benefit from Message Passing
by: Xie, Jiaqing, et al.
Published: (2024)