Cover Image

The Achilles' Heel of LLMs: How Altering a Handful of Neurons Can Cripple Language Abilities

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Qin, Zixuan, Yu, Qingchen, Lyu, Kunlin, Fan, Zhaoxin, Sun, Yifan
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Exposing the Achilles' Heel: Evaluating LLMs Ability to Handle Mistakes in Mathematical Reasoning
by: Singh, Joykirat, et al.
Published: (2024)

Identifying the Achilles' Heel: An Iterative Method for Dynamically Uncovering Factual Errors in Large Language Models
by: Wang, Wenxuan, et al.
Published: (2024)

Achilles' Heels: Vulnerable Record Identification in Synthetic Data Publishing
by: Meeus, Matthieu, et al.
Published: (2023)

The Achilles Heel of AI: Fundamentals of Risk-Aware Training Data for High-Consequence Models
by: Cook, Dave, et al.
Published: (2025)

The Sword, Shield, and Achilles' Heel: Characterizing the Linguistic Inductive Bias of Large Language Models for Spatial Reasoning in Navigation Planning
by: Zhang, Xudong, et al.
Published: (2026)

Can Structured Templates Facilitate LLMs in Tackling Harder Tasks? : An Exploration of Scaling Laws by Difficulty
by: Yang, Zhichao, et al.
Published: (2025)

Inductive or Deductive? Rethinking the Fundamental Reasoning Abilities of LLMs
by: Cheng, Kewei, et al.
Published: (2024)

How Far Are We on the Decision-Making of LLMs? Evaluating LLMs' Gaming Ability in Multi-Agent Environments
by: Huang, Jen-tse, et al.
Published: (2024)

[WIP] Jailbreak Paradox: The Achilles' Heel of LLMs
by: Rao, Abhinav, et al.
Published: (2024)

Burger: Robust Graph Denoising-augmentation Fusion and Multi-semantic Modeling in Social Recommendation
by: Lan, Yuqin, et al.
Published: (2025)

Can MLLMs Absorb Math Reasoning Abilities from LLMs as Free Lunch?
by: Hu, Yijie, et al.
Published: (2025)

How Does Alignment Enhance LLMs' Multilingual Capabilities? A Language Neurons Perspective
by: Zhang, Shimao, et al.
Published: (2025)

FineSteer: A Unified Framework for Fine-Grained Inference-Time Steering in Large Language Models
by: Weng, Zixuan, et al.
Published: (2026)

Can LLMs Reliably Simulate Real Students' Abilities in Mathematics and Reading Comprehension?
by: Srivatsa, KV Aditya, et al.
Published: (2025)

Neuron-Guided Interpretation of Code LLMs: Where, Why, and How?
by: Yin, Zhe, et al.
Published: (2025)

Decomposing Theory of Mind: How Emotional Processing Mediates ToM Abilities in LLMs
by: Chulo, Ivan, et al.
Published: (2025)

HalluSAE: Detecting Hallucinations in Large Language Models via Sparse Auto-Encoders
by: Chen, Boshui, et al.
Published: (2026)

CRANE: Causal Relevance Analysis of Language-Specific Neurons in Multilingual Large Language Models
by: Le, Yifan, et al.
Published: (2026)

How Many Instructions Can LLMs Follow at Once?
by: Jaroslawicz, Daniel, et al.
Published: (2025)

Exposing and Defending the Achilles' Heel of Video Mixture-of-Experts
by: Wang, Songping, et al.
Published: (2026)

Why Does New Knowledge Create Messy Ripple Effects in LLMs?
by: Qin, Jiaxin, et al.
Published: (2024)

Counting Objects in a Robotic Hand
by: Tsow, Francis, et al.
Published: (2024)

H-Neurons: On the Existence, Impact, and Origin of Hallucination-Associated Neurons in LLMs
by: Gao, Cheng, et al.
Published: (2025)

Distilling LLMs' Decomposition Abilities into Compact Language Models
by: Tarasov, Denis, et al.
Published: (2024)

MSCR: Exploring the Vulnerability of LLMs' Mathematical Reasoning Abilities Using Multi-Source Candidate Replacement
by: Sun, Zhishen, et al.
Published: (2025)

Loop Neural Networks for Parameter Sharing
by: Ng, Kei-Sing, et al.
Published: (2024)

IntrinsicVoice: Empowering LLMs with Intrinsic Real-time Voice Interaction Abilities
by: Zhang, Xin, et al.
Published: (2024)

TMGBench: A Systematic Game Benchmark for Evaluating Strategic Reasoning Abilities of LLMs
by: Wang, Haochuan, et al.
Published: (2024)

Can Large Language Models Make the Grade? An Empirical Study Evaluating LLMs Ability to Mark Short Answer Questions in K-12 Education
by: Henkel, Owen, et al.
Published: (2024)

The End of Reward Engineering: How LLMs Are Redefining Multi-Agent Coordination
by: Su, Haoran, et al.
Published: (2026)

Improving LLMs' Generalized Reasoning Abilities by Graph Problems
by: Zhang, Qifan, et al.
Published: (2025)

RoboPARA: Dual-Arm Robot Planning with Parallel Allocation and Recomposition Across Tasks
by: Duan, Shiying, et al.
Published: (2025)

Can Language Models Enable In-Context Database?
by: Pan, Yu, et al.
Published: (2024)

Extramedullary Disease—Achilles Heel in Myeloma?
by: Shaji Kumar, et al.
Published: (2025)

Neural FOXP2 -- Language Specific Neuron Steering for Targeted Language Improvement in LLMs
by: Saha, Anusa, et al.
Published: (2026)

The Butterfly Effect of Altering Prompts: How Small Changes and Jailbreaks Affect Large Language Model Performance
by: Salinas, Abel, et al.
Published: (2024)

Unveiling the Compositional Ability Gap in Vision-Language Reasoning Model
by: Li, Tianle, et al.
Published: (2025)

Gesture2Speech: How Far Can Hand Movements Shape Expressive Speech?
by: Kumar, Lokesh, et al.
Published: (2026)

How Can We Effectively Expand the Vocabulary of LLMs with 0.01GB of Target Language Text?
by: Yamaguchi, Atsuki, et al.
Published: (2024)

Detecting the Disturbance: A Nuanced View of Introspective Abilities in LLMs
by: Hahami, Ely, et al.
Published: (2025)