Cover Image

The Hallucination Tax of Reinforcement Finetuning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Song, Linxin, Shi, Taiwei, Zhao, Jieyu
Format:	Preprint
Published:	2025
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Efficient Reinforcement Finetuning via Adaptive Curriculum Learning
by: Shi, Taiwei, et al.
Published: (2025)

Discovering Knowledge Deficiencies of Language Models on Massive Knowledge Base
by: Song, Linxin, et al.
Published: (2025)

Safer-Instruct: Aligning Language Models with Automated Preference Data
by: Shi, Taiwei, et al.
Published: (2023)

Video-Based Reward Modeling for Computer-Use Agents
by: Song, Linxin, et al.
Published: (2026)

CoAct-1: Computer-using Multi-Agent System with Coding Actions
by: Song, Linxin, et al.
Published: (2025)

Self-Evolving LLM Memory Extraction Across Heterogeneous Tasks
by: Yang, Yuqing, et al.
Published: (2026)

Experiential Reinforcement Learning
by: Shi, Taiwei, et al.
Published: (2026)

Mitigating Bias in Locally Constrained Decoding via Tractable Proposals
by: Dang, Meihua, et al.
Published: (2026)

Mitigating Large Language Model Hallucination with Faithful Finetuning
by: Hu, Minda, et al.
Published: (2024)

Offline Training of Language Model Agents with Functions as Learnable Weights
by: Zhang, Shaokun, et al.
Published: (2024)

Adaptive In-conversation Team Building for Language Model Agents
by: Song, Linxin, et al.
Published: (2024)

STEER-BENCH: A Benchmark for Evaluating the Steerability of Large Language Models
by: Chen, Kai, et al.
Published: (2025)

Converted, Not Equivalent: Benchmarking Codebase Conversion via Observational Equivalence
by: Song, Linxin, et al.
Published: (2026)

From Hallucination to Structure Snowballing: The Alignment Tax of Constrained Decoding in LLM Reflection
by: Zhou, Hongxu
Published: (2026)

Finetune-RAG: Fine-Tuning Language Models to Resist Hallucination in Retrieval-Augmented Generation
by: Lee, Zhan Peng, et al.
Published: (2025)

Trojan-Speak: Bypassing Constitutional Classifiers with No Jailbreak Tax via Adversarial Finetuning
by: Sel, Bilgehan, et al.
Published: (2026)

Unfamiliar Finetuning Examples Control How Language Models Hallucinate
by: Kang, Katie, et al.
Published: (2024)

MARCH: Multi-Agent Reinforced Self-Check for LLM Hallucination
by: Li, Zhuo, et al.
Published: (2026)

One Model, All Roles: Multi-Turn, Multi-Agent Self-Play Reinforcement Learning for Conversational Social Intelligence
by: Jiang, Bowen, et al.
Published: (2026)

WildFeedback: Aligning LLMs With In-situ User Interactions And Feedback
by: Shi, Taiwei, et al.
Published: (2024)

How Susceptible are Large Language Models to Ideological Manipulation?
by: Chen, Kai, et al.
Published: (2024)

BigCharts-R1: Enhanced Chart Reasoning with Visual Reinforcement Finetuning
by: Masry, Ahmed, et al.
Published: (2025)

Vanishing Gradients in Reinforcement Finetuning of Language Models
by: Razin, Noam, et al.
Published: (2023)

Better Explain Transformers by Illuminating Important Information
by: Song, Linxin, et al.
Published: (2024)

Explaining Length Bias in LLM-Based Preference Evaluations
by: Hu, Zhengyu, et al.
Published: (2024)

The Format Tax
by: Lee, Ivan Yee, et al.
Published: (2026)

Reinforcement Learning with Semantic Rewards Enables Low-Resource Language Expansion without Alignment Tax
by: Su, Zeli, et al.
Published: (2026)

A Simple "Motivation" Can Enhance Reinforcement Finetuning of Large Reasoning Models
by: Zhang, Junjie, et al.
Published: (2025)

Synthesizing Privacy-Preserving Text Data via Finetuning without Finetuning Billion-Scale LLMs
by: Tan, Bowen, et al.
Published: (2025)

Stop Rewarding Hallucinated Steps: Faithfulness-Aware Step-Level Reinforcement Learning for Small Reasoning Models
by: Nie, Shuo, et al.
Published: (2026)

CoAnnotating: Uncertainty-Guided Work Allocation between Human and Large Language Models for Data Annotation
by: Li, Minzhi, et al.
Published: (2023)

KnowLA: Enhancing Parameter-efficient Finetuning with Knowledgeable Adaptation
by: Luo, Xindi, et al.
Published: (2024)

Alleviating Hallucinations of Large Language Models through Induced Hallucinations
by: Zhang, Yue, et al.
Published: (2023)

Large Language Models to Diffusion Finetuning
by: Cetin, Edoardo, et al.
Published: (2025)

Understanding the Effects of Domain Finetuning on LLMs
by: Tanwar, Eshaan, et al.
Published: (2025)

GradShield: Alignment Preserving Finetuning
by: Hu, Zhanhao, et al.
Published: (2026)

Locking Down the Finetuned LLMs Safety
by: Zhu, Minjun, et al.
Published: (2024)

Finetuning LLMs for Comparative Assessment Tasks
by: Raina, Vatsal, et al.
Published: (2024)

Detecting LLM Fact-conflicting Hallucinations Enhanced by Temporal-logic-based Reasoning
by: Li, Ningke, et al.
Published: (2025)

When Scaling Meets LLM Finetuning: The Effect of Data, Model and Finetuning Method
by: Zhang, Biao, et al.
Published: (2024)