{"total":45,"rows":[{"id":"2406.16008","title":"Found in the Middle: Calibrating Positional Attention Bias Improves Long Context Utilization","created":"2024-06-23","cited_by_count":101,"area":null},{"id":"2409.00729","title":"ContextCite: Attributing Model Generation to Context","created":"2024-09-01","cited_by_count":98,"area":null},{"id":"2403.04797","title":"Found in the Middle: How Language Models Use Long Contexts Better via Plug-and-Play Positional Encoding","created":"2024-03-05","cited_by_count":72,"area":null},{"id":"2407.01100","title":"Eliminating Position Bias of Language Models: A Mechanistic Approach","created":"2024-07-01","cited_by_count":65,"area":null},{"id":"2406.14673","title":"Insights into LLM Long-Context Failures: When Transformers Know but Don't Tell","created":"2024-06-20","cited_by_count":36,"area":null},{"id":"2312.04455","title":"Fortify the Shortest Stave in Attention: Enhancing Context Awareness of Large Language Models for Effective Tool Use","created":"2023-12-07","cited_by_count":27,"area":null},{"id":"2502.08767","title":"SelfElicit: Your Language Model Secretly Knows Where is the Relevant Evidence","created":"2025-02-12","cited_by_count":18,"area":null},{"id":"2406.19598","title":"Mixture of In-Context Experts Enhance LLMs' Long Context Awareness","created":"2024-06-28","cited_by_count":17,"area":null},{"id":"2504.13752","title":"Learning to Attribute with Attention","created":"2025-04-18","cited_by_count":13,"area":null},{"id":"2406.18312","title":"AI-native Memory: A Pathway from LLMs Towards AGI","created":"2024-06-26","cited_by_count":12,"area":null},{"id":"2510.10276","title":"Lost in the Middle: An Emergent Property from Information Retrieval Demands in LLMs","created":"2025-10-11","cited_by_count":9,"area":null},{"id":"2507.03194","title":"Quantifying Cognitive Bias Induction in LLM-Generated Content","created":"2025-07-03","cited_by_count":7,"area":null},{"id":"2605.11161","title":"Interpretability Can Be Actionable","created":"2026-05-11","cited_by_count":7,"area":null},{"id":"2402.12170","title":"Where is the answer? Investigating Positional Bias in Language Model Knowledge Extraction","created":"2024-02-16","cited_by_count":6,"area":null},{"id":"2406.17095","title":"Attention Instruction: Amplifying Attention in the Middle via Prompting","created":"2024-06-24","cited_by_count":6,"area":null},{"id":"2312.11193","title":"Training With \"Paraphrasing the Original Text\" Teaches LLM to Better Retrieve in Long-context Tasks","created":"2023-12-18","cited_by_count":5,"area":null},{"id":"2505.16134","title":"Beyond Early-Token Bias: Model-Specific and Language-Specific Position Effects in Multilingual LLMs","created":"2025-05-22","cited_by_count":5,"area":null},{"id":"2507.13949","title":"Exploiting Primacy Effect To Improve Large Language Models","created":"2025-07-18","cited_by_count":5,"area":null},{"id":"2602.19969","title":"ReAttn: Improving Attention-based Re-ranking via Attention Re-weighting","created":"2026-02-23","cited_by_count":5,"area":null},{"id":"2502.06902","title":"Emergence of Episodic Memory in Transformers: Characterizing Changes in Temporal Structure of Attention Scores During Training","created":"2025-02-09","cited_by_count":4,"area":null},{"id":"2512.14391","title":"RePo: Language Models with Context Re-Positioning","created":"2025-12-16","cited_by_count":4,"area":null},{"id":"2401.04881","title":"Attendre: Wait To Attend By Retrieval With Evicted Queries in Memory-Based Transformers for Long Context Processing","created":"2024-01-10","cited_by_count":3,"area":null},{"id":"2406.02536","title":"Mitigate Position Bias in Large Language Models via Scaling a Single Dimension","created":"2024-06-04","cited_by_count":3,"area":null},{"id":"2501.14183","title":"VarDrop: Enhancing Training Efficiency by Reducing Variate Redundancy in Periodic Time Series Forecasting","created":"2025-01-24","cited_by_count":3,"area":null},{"id":"2502.08662","title":"RoToR: Towards More Reliable Responses for Order-Invariant Inputs","created":"2025-02-10","cited_by_count":3,"area":null},{"id":"2512.19154","title":"Beyond Sliding Windows: Learning to Manage Memory in Non-Markovian Environments","created":"2025-12-22","cited_by_count":3,"area":null},{"id":"2603.17484","title":"Learning When to Attend: Conditional Memory Access for Long-Context LLMs","created":"2026-03-18","cited_by_count":3,"area":null},{"id":"2502.06004","title":"Analysis of LLM as a grammatical feature tagger for African American English","created":"2025-02-09","cited_by_count":2,"area":null},{"id":"2502.08436","title":"From Haystack to Needle: Label Space Reduction for Zero-shot Classification","created":"2025-02-12","cited_by_count":2,"area":null},{"id":"2510.09347","title":"LLP: LLM-Based Product Pricing in E-commerce","created":"2025-10-10","cited_by_count":2,"area":null},{"id":"2601.07994","title":"DYCP: Dynamic Context Pruning for Long-Form Dialogue with LLMs","created":"2026-01-12","cited_by_count":2,"area":null},{"id":"2604.10027","title":"SinkTrack: Attention Sink based Context Anchoring for Large Language Models","created":"2026-04-11","cited_by_count":2,"area":null},{"id":"2406.16833","title":"USDC: A Dataset of $\\underline{U}$ser $\\underline{S}$tance and $\\underline{D}$ogmatism in Long $\\underline{C}$onversations","created":"2024-06-24","cited_by_count":1,"area":null},{"id":"2503.04355","title":"Layer-Specific Scaling of Positional Encodings for Superior Long-Context Modeling","created":"2025-03-06","cited_by_count":1,"area":null},{"id":"2507.17262","title":"VisionTrap: Unanswerable Questions On Visual Data","created":"2025-07-23","cited_by_count":1,"area":null},{"id":"2508.02308","title":"LaMPE: Length-aware Multi-grained Positional Encoding for Adaptive Long-context Scaling Without Training","created":"2025-08-04","cited_by_count":1,"area":null},{"id":"2512.13109","title":"Uncovering the Role of Initial Saliency in U-Shaped Attention Bias: Scaling Initial Token Weight for Enhanced Long-Text Processing","created":"2025-12-15","cited_by_count":1,"area":null},{"id":"2406.02002","title":"Position Debiasing Fine-Tuning for Causal Perception in Long-Term Dialogue","created":"2024-06-04","cited_by_count":0,"area":null},{"id":"2410.23066","title":"Don't Pay Attention, PLANT It: Pretraining Attention via Learning-to-Rank","created":"2024-10-30","cited_by_count":0,"area":null},{"id":"2506.08371","title":"Mitigating Posterior Salience Attenuation in Long-Context LLMs with Positional Contrastive Decoding","created":"2025-06-10","cited_by_count":0,"area":null},{"id":"2601.03269","title":"The Instruction Gap: LLMs get lost in Following Instruction","created":"2025-12-19","cited_by_count":0,"area":null},{"id":"2603.16292","title":"Attention-guided Evidence Grounding for Spoken Question Answering","created":"2026-03-17","cited_by_count":0,"area":null},{"id":"2604.02200","title":"Towards Position-Robust Talent Recommendation via Large Language Models","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2606.27793","title":"Position Bias Correction is Insufficient for One-Pass Attention Sorting","created":"2026-06-26","cited_by_count":0,"area":null},{"id":"2608.20853","title":"MGAL: A Multilingual Granularity-Aware Long-Context Benchmark","created":"2026-08-21","cited_by_count":0,"area":null}],"next_cursor":null}