Cover Image

The Curse of Helpfulness: Inverse Scaling Law in Robustness to Distractor Instructions via DistractionIF

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Su, Zeli, Xu, Zhankai, Chen, Tianlei, Zheng, Longfei, Zhang, Xiaolu, Zhou, Jun, Zhang, Wentao
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Source-Grounded Semantic Reinforcement Learning for Low-Resource Target-Language Generation
by: Su, Zeli, et al.
Published: (2026)

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

LLMs can be easily Confused by Instructional Distractions
by: Hwang, Yerin, et al.
Published: (2025)

Improving Natural Language Understanding for LLMs via Large-Scale Instruction Synthesis
by: Yuan, Lin, et al.
Published: (2025)

Uncovering Scaling Laws for Large Language Models via Inverse Problems
by: Verma, Arun, et al.
Published: (2025)

Breaking the Curse of Repulsion: Optimistic Distributionally Robust Policy Optimization for Off-Policy Generative Recommendation
by: Jiang, Jie, et al.
Published: (2026)

Seirênes: Adversarial Self-Play with Evolving Distractions for LLM Reasoning
by: Zhang, Chi, et al.
Published: (2026)

Active Testing of Large Language Models via Approximate Neyman Allocation
by: Liu, Zeli, et al.
Published: (2026)

Scaling Laws for Educational AI Agents
by: Wu, Mengsong, et al.
Published: (2026)

Distractor Injection Attacks on Large Reasoning Models: Characterization and Defense
by: Zhang, Zhehao, et al.
Published: (2025)

Towards Reliable LLM Evaluation: Correcting the Winner's Curse in Adaptive Benchmarking
by: Xu, Yang, et al.
Published: (2026)

An Analysis and Mitigation of the Reversal Curse
by: Lv, Ang, et al.
Published: (2023)

MAQInstruct: Instruction-based Unified Event Relation Extraction
by: Xu, Jun, et al.
Published: (2025)

SHRP: Specialized Head Routing and Pruning for Efficient Encoder Compression
by: Su, Zeli, et al.
Published: (2025)

Breaking the Martingale Curse: Multi-Agent Debate via Asymmetric Cognitive Potential Energy
by: Liu, Yuhan, et al.
Published: (2026)

ImitDiff: Transferring Foundation-Model Priors for Distraction Robust Visuomotor Policy
by: Dong, Yuhang, et al.
Published: (2025)

Boosting Medical Image Synthesis via Registration-guided Consistency and Disentanglement Learning
by: Li, Chuanpu, et al.
Published: (2024)

Controllable Unlearning for Image-to-Image Generative Models via $\varepsilon$-Constrained Optimization
by: Feng, Xiaohua, et al.
Published: (2024)

DistractMIA: Black-Box Membership Inference on Vision-Language Models via Semantic Distraction
by: Tang, Hongyi, et al.
Published: (2026)

Enhancing Rare Codes via Probability-Biased Directed Graph Attention for Long-Tail ICD Coding
by: Chen, Tianlei, et al.
Published: (2025)

Multilingual Encoder Knows more than You Realize: Shared Weights Pretraining for Extremely Low-Resource Languages
by: Su, Zeli, et al.
Published: (2025)

FlipVQA: Scaling Multi-modal Instruction Tuning via Textbook-to-Knowledge Synthesis
by: Wong, Zhen Hao, et al.
Published: (2025)

IF-GEO: Conflict-Aware Instruction Fusion for Multi-Query Generative Engine Optimization
by: Zhou, Heyang, et al.
Published: (2026)

Seeing but Not Thinking: Routing Distraction in Multimodal Mixture-of-Experts
by: Xu, Haolei, et al.
Published: (2026)

Mitigating Cross-Modal Distraction and Ensuring Geometric Feasibility via Affordance-Guided and Self-Consistent MLLMs for Task Planning in Instruction-Following Manipulation
by: Shen, Yu-Hong, et al.
Published: (2025)

Reimagination with Test-time Observation Interventions: Distractor-Robust World Model Predictions for Visual Model Predictive Control
by: Chen, Yuxin, et al.
Published: (2025)

The Curse of Depth in Large Language Models
by: Sun, Wenfang, et al.
Published: (2025)

Towards Precise Scaling Laws for Video Diffusion Transformers
by: Yin, Yuanyang, et al.
Published: (2024)

Robust Smart Contract Vulnerability Detection via Contrastive Learning-Enhanced Granular-ball Training
by: Wang, Zeli, et al.
Published: (2026)

When Slower Isn't Truer: Inverse Scaling Law of Truthfulness in Multimodal Reasoning
by: Fang, Sitong, et al.
Published: (2025)

Season-Independent PV Disaggregation Using Multi-Scale Net Load Temporal Feature Extraction and Weather Factor Fusion
by: Chen, Xiaolu, et al.
Published: (2025)

Dispelling the Curse of Singularities in Neural Network Optimizations
by: Cao, Hengjie, et al.
Published: (2026)

Scaling Laws for Speculative Decoding
by: Yan, Siyuan, et al.
Published: (2025)

InverseCoder: Self-improving Instruction-Tuned Code LLMs with Inverse-Instruct
by: Wu, Yutong, et al.
Published: (2024)

HLER: Human-in-the-Loop Economic Research via Multi-Agent Pipelines for Empirical Discovery
by: Zhu, Chen, et al.
Published: (2026)

P$^2$ Law: Scaling Law for Post-Training After Model Pruning
by: Chen, Xiaodong, et al.
Published: (2024)

Bootstrapping your behavior: a new pretraining strategy for user behavior sequence data
by: Wu, Weichang, et al.
Published: (2025)

Unifying Bayesian Flow Networks and Diffusion Models through Stochastic Differential Equations
by: Xue, Kaiwen, et al.
Published: (2024)

Universal Smoothness via Bernstein Polynomials: A Constructive Approximation Approach for Activation Functions
by: Zhang, Wentao, et al.
Published: (2026)

Calibrating Verbalized Confidence with Self-Generated Distractors
by: Wang, Victor, et al.
Published: (2025)