Cover Image

Computation Mechanism Behind LLM Position Generalization

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Han, Chi, Ji, Heng
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Following the Whispers of Values: Unraveling Neural Mechanisms Behind Value-Oriented Behaviors in LLMs
by: Hu, Ling, et al.
Published: (2025)

Tracing Thought: Using Chain-of-Thought Reasoning to Identify the LLM Behind AI-Generated Text
by: Agrahari, Shifali, et al.
Published: (2025)

Understanding Emergent In-Context Learning from a Kernel Regression Perspective
by: Han, Chi, et al.
Published: (2023)

LM-Infinite: Zero-Shot Extreme Length Generalization for Large Language Models
by: Han, Chi, et al.
Published: (2023)

Rationale Behind Essay Scores: Enhancing S-LLM's Multi-Trait Essay Scoring with Rationale Generated by LLMs
by: Chu, SeongYeub, et al.
Published: (2024)

Beyond Reactive Safety: Risk-Aware LLM Alignment via Long-Horizon Simulation
by: Sun, Chenkai, et al.
Published: (2025)

Controllable Context Sensitivity and the Knob Behind It
by: Minder, Julian, et al.
Published: (2024)

oMeBench: Towards Robust Benchmarking of LLMs in Organic Mechanism Elucidation and Reasoning
by: Xu, Ruiling, et al.
Published: (2025)

What Features in Prompts Jailbreak LLMs? Investigating the Mechanisms Behind Attacks
by: Kirch, Nathalie, et al.
Published: (2024)

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

Executable Code Actions Elicit Better LLM Agents
by: Wang, Xingyao, et al.
Published: (2024)

Stage-wise Fine-tuning for Graph-to-Text Generation
by: Wang, Qingyun, et al.
Published: (2021)

Forest-of-Thought: Scaling Test-Time Compute for Enhancing LLM Reasoning
by: Bi, Zhenni, et al.
Published: (2024)

Carrot and Stick: Inducing Self-Motivation with Positive & Negative Feedback
by: Sohn, Jimin, et al.
Published: (2024)

Peeking Behind Closed Doors: Risks of LLM Evaluation by Private Data Curators
by: Bansal, Hritik, et al.
Published: (2025)

CacheFocus: Dynamic Cache Re-Positioning for Efficient Retrieval-Augmented Generation
by: Lee, Kun-Hui, et al.
Published: (2025)

Towards Better Generalization in Open-Domain Question Answering by Mitigating Context Memorization
by: Zhang, Zixuan, et al.
Published: (2024)

No Reader Left Behind: Multi-Agent Summaries Everyone Can Understand
by: Jung, Jimin, et al.
Published: (2026)

The Why Behind the Action: Unveiling Internal Drivers via Agentic Attribution
by: Qian, Chen, et al.
Published: (2026)

Rethinking the Reranker: Boundary-Aware Evidence Selection for Robust Retrieval-Augmented Generation
by: Sun, Jiashuo, et al.
Published: (2026)

Schema-Guided Culture-Aware Complex Event Simulation with Multi-Agent Role-Play
by: Li, Sha, et al.
Published: (2024)

Split and Merge: Aligning Position Biases in LLM-based Evaluators
by: Li, Zongjie, et al.
Published: (2023)

UserHarness: Harnessing User Minds for Stronger Agent Theory-of-Mind
by: Qian, Cheng, et al.
Published: (2026)

SyncMind: Measuring Agent Out-of-Sync Recovery in Collaborative Software Engineering
by: Guo, Xuehang, et al.
Published: (2025)

MentalArena: Self-play Training of Language Models for Diagnosis and Treatment of Mental Health Disorders
by: Li, Cheng, et al.
Published: (2024)

StoryCoder: Narrative Reformulation for Structured Reasoning in LLM Code Generation
by: Jang, Geonhui, et al.
Published: (2026)

Automating Intervention Discovery from Scientific Literature: A Progressive Ontology Prompting and Dual-LLM Framework
by: Hu, Yuting, et al.
Published: (2024)

Extending Token Computation for LLM Reasoning
by: Liao, Bingli, et al.
Published: (2024)

LLM-Confidence Reranker: A Training-Free Approach for Enhancing Retrieval-Augmented Generation Systems
by: Song, Zhipeng, et al.
Published: (2026)

Prompt-prompted Adaptive Structured Pruning for Efficient LLM Generation
by: Dong, Harry, et al.
Published: (2024)

ReviewRobot: Explainable Paper Review Generation based on Knowledge Synthesis
by: Wang, Qingyun, et al.
Published: (2020)

On Reasoning Behind Next Occupation Recommendation
by: Dong, Shan, et al.
Published: (2026)

LDC: Learning to Generate Research Idea with Dynamic Control
by: Li, Ruochen, et al.
Published: (2024)

Computer Environments Elicit General Agentic Intelligence in LLMs
by: Cheng, Daixuan, et al.
Published: (2026)

Self-Improving LLM Agents at Test-Time
by: Acikgoz, Emre Can, et al.
Published: (2025)

Leveraging Retrieval-Augmented Generation for Culturally Inclusive Hakka Chatbots: Design Insights and User Perceptions
by: Chang, Chen-Chi, et al.
Published: (2024)

Languages Still Left Behind: Toward a Better Multilingual Machine Translation Benchmark
by: Taguchi, Chihiro, et al.
Published: (2025)

Who Are You Behind the Screen? Implicit MBTI and Gender Detection Using Artificial Intelligence
by: Shahnazari, Kourosh, et al.
Published: (2025)

Position: Pause Recycling LoRAs and Prioritize Mechanisms to Uncover Limits and Effectiveness
by: Chen, Mei-Yen, et al.
Published: (2025)

Leave No Document Behind: Benchmarking Long-Context LLMs with Extended Multi-Doc QA
by: Wang, Minzheng, et al.
Published: (2024)