Cover Image

Beyond Position Bias: Shifting Context Compression from Position-Driven to Semantic-Driven

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Tang, Jiwei, Huang, Zhijing, Zhang, Xinyu, Zhang, Chen Jason, Yu, Jianxing, Zheng, Libin, Meng, Rui, Yin, Jian
Format:	Preprint
Published:	2026
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

COMI: Coarse-to-fine Context Compression via Marginal Information Gain
by: Tang, Jiwei, et al.
Published: (2026)

Position IDs Matter: An Enhanced Position Layout for Efficient Context Compression in Large Language Models
by: Zhao, Runsong, et al.
Published: (2024)

More Thinking, More Bias: Length-Driven Position Bias in Reasoning Models
by: Wang, Xiao
Published: (2026)

CoS: Towards Optimal Event Scheduling via Chain-of-Scheduling
by: Zhao, Yiming, et al.
Published: (2025)

Position Bias Mitigates Position Bias:Mitigate Position Bias Through Inter-Position Knowledge Distillation
by: Wang, Yifei, et al.
Published: (2025)

GMSA: Enhancing Context Compression via Group Merging and Layer Semantic Alignment
by: Tang, Jiwei, et al.
Published: (2025)

Position-Aware Parameter Efficient Fine-Tuning Approach for Reducing Positional Bias in LLMs
by: Zhang, Zheng, et al.
Published: (2024)

Less Is More: Elevating RAG via Performance-Driven Context Compression
by: Cui, Ziqiang, et al.
Published: (2025)

Positional Biases Shift as Inputs Approach Context Window Limits
by: Veseli, Blerta, et al.
Published: (2025)

Position: LLMs Must Use Functor-Based and RAG-Driven Bias Mitigation for Fairness
by: Ranjan, Ravi, et al.
Published: (2026)

Perception Compressor: A Training-Free Prompt Compression Framework in Long Context Scenarios
by: Tang, Jiwei, et al.
Published: (2024)

Layer-wise Positional Bias in Short-Context Language Modeling
by: Rahimi, Maryam, et al.
Published: (2026)

Found in the Middle: Calibrating Positional Attention Bias Improves Long Context Utilization
by: Hsieh, Cheng-Yu, et al.
Published: (2024)

Do Large Language Models Plan Answer Positions? Position Bias in Multiple-Choice Question Generation
by: Tang, Xuemei, et al.
Published: (2026)

Read As Human: Compressing Context via Parallelizable Close Reading and Skimming
by: Tang, Jiwei, et al.
Published: (2026)

Autoencoding-Free Context Compression for LLMs via Contextual Semantic Anchors
by: Liu, Xin, et al.
Published: (2025)

Beyond Real: Imaginary Extension of Rotary Position Embeddings for Long-Context LLMs
by: Liu, Xiaoran, et al.
Published: (2025)

Data Distribution Matters: A Data-Centric Perspective on Context Compression for Large Language Model
by: Lv, Kangtao, et al.
Published: (2026)

PoC: Performance-oriented Context Compression for Large Language Models via Performance Prediction
by: Zhao, Runsong, et al.
Published: (2026)

Self-Consistency Falls Short! The Adverse Effects of Positional Bias on Long-Context Problems
by: Byerly, Adam, et al.
Published: (2024)

ReFineG: Synergizing Small Supervised Models and LLMs for Low-Resource Grounded Multimodal NER
by: Tang, Jielong, et al.
Published: (2025)

Where to show Demos in Your Prompt: A Positional Bias of In-Context Learning
by: Cobbina, Kwesi, et al.
Published: (2025)

AdmTree: Compressing Lengthy Context with Adaptive Semantic Trees
by: Li, Yangning, et al.
Published: (2025)

Hearing the Order: Investigating Position Bias in Large Audio-Language Models
by: Lin, Yu-Xiang, et al.
Published: (2025)

Eliminating Position Bias of Language Models: A Mechanistic Approach
by: Wang, Ziqi, et al.
Published: (2024)

Where is the answer? Investigating Positional Bias in Language Model Knowledge Extraction
by: Saito, Kuniaki, et al.
Published: (2024)

On Positional Bias of Faithfulness for Long-form Summarization
by: Wan, David, et al.
Published: (2024)

Layer-Specific Scaling of Positional Encodings for Superior Long-Context Modeling
by: Wang, Zhenghua, et al.
Published: (2025)

Submodular Context Partitioning and Compression for In-Context Learning
by: Zheng, Shaoyi, et al.
Published: (2025)

Beyond Early-Token Bias: Model-Specific and Language-Specific Position Effects in Multilingual LLMs
by: Menschikov, Mikhail, et al.
Published: (2025)

Context-aware Rotary Position Embedding
by: Veisi, Ali, et al.
Published: (2025)

Token Homogenization under Positional Bias
by: Yusupov, Viacheslav, et al.
Published: (2025)

Positional Bias in Long-Document Ranking: Impact, Assessment, and Mitigation
by: Boytsov, Leonid, et al.
Published: (2022)

An Efficient Recipe for Long Context Extension via Middle-Focused Positional Encoding
by: Wu, Tong, et al.
Published: (2024)

Mitigating Coordinate Prediction Bias from Positional Encoding Failures
by: Tao, Xingjian, et al.
Published: (2025)

Wavelet-based Positional Representation for Long Context
by: Oka, Yui, et al.
Published: (2025)

A Pilot Empirical Study on When and How to Use Knowledge Graphs as Retrieval Augmented Generation
by: Yuan, Xujie, et al.
Published: (2025)

Single-Position Intervention Fails: Distributed Output Templates Drive In-Context Learning
by: Cheng, Bryan, et al.
Published: (2026)

Mitigate Position Bias in Large Language Models via Scaling a Single Dimension
by: Yu, Yijiong, et al.
Published: (2024)

Positional Failures in Long-Context LLMs: A Blind Spot in Reasoning Benchmarks
by: Zhang, Chuyifei, et al.
Published: (2026)