Retrieval Head Mechanistically Explains Long-Context Factuality | Paper Citation Record

Observation c25c24a4-8f2c-4353-ae1c-8b957dc7ce3b · inbound

PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling cites this paper.

PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling Retrieval Head Mechanistically Explains Long-Context Factuality

Reference 22

Resolution: verified exact; arxiv_id, observed 2026-05-12T09:58:29.212025Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation e6564002-5de1-46ec-94b7-1698ddbae20a · inbound

MiniKV: Pushing the Limits of LLM Inference via 2-Bit Layer-Discriminative KV Cache cites this paper.

MiniKV: Pushing the Limits of LLM Inference via 2-Bit Layer-Discriminative KV Cache Retrieval Head Mechanistically Explains Long-Context Factuality

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-12T11:37:07.659393Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b4fab4bd-f1be-45ec-8d9c-9b863cffc5e8 · inbound

DENIAHL: In-Context Features Influence LLM Needle-In-A-Haystack Abilities cites this paper.

DENIAHL: In-Context Features Influence LLM Needle-In-A-Haystack Abilities Retrieval Head Mechanistically Explains Long-Context Factuality

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-12T10:17:30.325277Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c2e8ed2-e5df-4cb6-a374-105a8fccc643 · inbound

SCOPE: Optimizing Key-Value Cache Compression in Long-context Generation cites this paper.

SCOPE: Optimizing Key-Value Cache Compression in Long-context Generation Retrieval Head Mechanistically Explains Long-Context Factuality

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-11T13:00:58.082752Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 79df74bb-f5ba-4c68-8ded-47b3a5571d29 · inbound

Attention Entropy is a Key Factor: An Analysis of Parallel Context Encoding with Full-attention-based Pre-trained Language Models cites this paper.

Attention Entropy is a Key Factor: An Analysis of Parallel Context Encoding with Full-attention-based Pre-trained Language Models Retrieval Head Mechanistically Explains Long-Context Factuality

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-11T10:33:43.116002Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 869874cb-d34a-415b-995d-a41bca3b2f75 · inbound

A Survey on Large Language Model Acceleration based on KV Cache Management cites this paper.

A Survey on Large Language Model Acceleration based on KV Cache Management Retrieval Head Mechanistically Explains Long-Context Factuality

Reference 148

Resolution: unresolved; no resolver link, observed 2026-08-11T00:38:48.336531Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68c8b5e5-fd10-44d4-9ead-1bba07f67a39 · inbound

Dynamic Attention-Guided Context Decoding for Mitigating Context Faithfulness Hallucinations in Large Language Models cites this paper.

Dynamic Attention-Guided Context Decoding for Mitigating Context Faithfulness Hallucinations in Large Language Models Retrieval Head Mechanistically Explains Long-Context Factuality

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-10T22:42:11.315885Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 03fc56b7-bc1a-45b5-8d83-9c7a0300f6f4 · inbound

Eliciting In-context Retrieval and Reasoning for Long-context Large Language Models cites this paper.

Eliciting In-context Retrieval and Reasoning for Long-context Large Language Models Retrieval Head Mechanistically Explains Long-Context Factuality

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-10T20:33:22.753472Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 623b0289-806d-4128-9d20-8bd2dfd7465c · inbound

Efficient Prompt Compression with Evaluator Heads for Long-Context Transformer Inference cites this paper.

Efficient Prompt Compression with Evaluator Heads for Long-Context Transformer Inference Retrieval Head Mechanistically Explains Long-Context Factuality

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-10T16:40:36.772401Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ed788b9-6d83-46d6-9767-f1fef880d790 · inbound

Improving Contextual Faithfulness of Large Language Models via Retrieval Heads-Induced Optimization cites this paper.

Improving Contextual Faithfulness of Large Language Models via Retrieval Heads-Induced Optimization Retrieval Head Mechanistically Explains Long-Context Factuality

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-10T15:51:52.638005Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 789e0f0c-50b4-4f78-83da-a4edb2d57cdc · inbound

Task-KV: Task-aware KV Cache Optimization via Semantic Differentiation of Attention Heads cites this paper.

Task-KV: Task-aware KV Cache Optimization via Semantic Differentiation of Attention Heads Retrieval Head Mechanistically Explains Long-Context Factuality

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-10T14:41:05.037675Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bfe100d2-a3c3-4b62-830a-a75d3e7ad1fd · inbound

LongDPO: Unlock Better Long-form Generation Abilities for LLMs via Critique-augmented Stepwise Information cites this paper.

LongDPO: Unlock Better Long-form Generation Abilities for LLMs via Critique-augmented Stepwise Information Retrieval Head Mechanistically Explains Long-Context Factuality

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-09T13:25:52.101276Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a3e2b4d0-6647-42c4-8a7e-ec9194fab777 · inbound

CryptoX : Compositional Reasoning Evaluation of Large Language Models cites this paper.

CryptoX : Compositional Reasoning Evaluation of Large Language Models Retrieval Head Mechanistically Explains Long-Context Factuality

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-08T18:34:26.794369Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2883a270-e414-4807-909d-47b065b6dd6b · inbound

Unveiling Simplicities of Attention: Adaptive Long-Context Head Identification cites this paper.

Unveiling Simplicities of Attention: Adaptive Long-Context Head Identification Retrieval Head Mechanistically Explains Long-Context Factuality

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-08T13:46:11.433213Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 43524d81-0b94-4a4e-aba6-91c87d1ec87a · inbound

Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism cites this paper.

Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism Retrieval Head Mechanistically Explains Long-Context Factuality

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-16T11:17:29.479315Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68f4bc23-0f97-4463-b84a-2221f2d7af7c · inbound

Towards Understanding the Nature of Attention with Low-Rank Sparse Decomposition cites this paper.

Towards Understanding the Nature of Attention with Low-Rank Sparse Decomposition Retrieval Head Mechanistically Explains Long-Context Factuality

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-16T05:21:34.087163Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d1e7c72-9bd7-49a3-8403-c1dcfea521f5 · inbound

AttentionInfluence: Adopting Attention Head Influence for Weak-to-Strong Pretraining Data Selection cites this paper.

AttentionInfluence: Adopting Attention Head Influence for Weak-to-Strong Pretraining Data Selection Retrieval Head Mechanistically Explains Long-Context Factuality

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-15T22:23:36.581532Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94619282-1e4e-48cd-8940-8dba8f746f5f · inbound

SEReDeEP: Hallucination Detection in Retrieval-Augmented Models via Semantic Entropy and Context-Parameter Fusion cites this paper.

SEReDeEP: Hallucination Detection in Retrieval-Augmented Models via Semantic Entropy and Context-Parameter Fusion Retrieval Head Mechanistically Explains Long-Context Factuality

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-15T22:18:56.859224Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c4a5725e-916b-458b-be25-4a4b7f704dc5 · inbound

CAFE: Retrieval Head-based Coarse-to-Fine Information Seeking to Enhance Multi-Document QA Capability cites this paper.

CAFE: Retrieval Head-based Coarse-to-Fine Information Seeking to Enhance Multi-Document QA Capability Retrieval Head Mechanistically Explains Long-Context Factuality

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-15T21:23:46.804370Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 07b867ad-aad0-49fb-b124-27f183b17be9 · inbound

Detection and Mitigation of Hallucination in Large Reasoning Models: A Mechanistic Perspective cites this paper.

Detection and Mitigation of Hallucination in Large Reasoning Models: A Mechanistic Perspective Retrieval Head Mechanistically Explains Long-Context Factuality

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-15T20:28:19.112399Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc76bb3d-3cd3-4345-aecf-0d23c1613ce8 · inbound

Calm-Whisper: Reduce Whisper Hallucination On Non-Speech By Calming Crazy Heads Down cites this paper.

Calm-Whisper: Reduce Whisper Hallucination On Non-Speech By Calming Crazy Heads Down Retrieval Head Mechanistically Explains Long-Context Factuality

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-15T20:27:12.008396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 06e312a4-ee12-416a-9d35-8c51fd801692 · inbound

ALPS: Attention Localization and Pruning Strategy for Efficient Alignment of Large Language Models cites this paper.

ALPS: Attention Localization and Pruning Strategy for Efficient Alignment of Large Language Models Retrieval Head Mechanistically Explains Long-Context Factuality

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-07T14:31:32.659055Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 874f5005-6dad-4369-872e-2e58e5f8ba99 · inbound

Stochastic Chameleons: Irrelevant Context Hallucinations Reveal Class-Based (Mis)Generalization in LLMs cites this paper.

Stochastic Chameleons: Irrelevant Context Hallucinations Reveal Class-Based (Mis)Generalization in LLMs Retrieval Head Mechanistically Explains Long-Context Factuality

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-07T13:09:24.345384Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1928aaf2-3c6e-47ef-b15e-9150072269f2 · inbound

REAL: Reading Out Transformer Activations for Precise Localization in Language Model Steering cites this paper.

REAL: Reading Out Transformer Activations for Precise Localization in Language Model Steering Retrieval Head Mechanistically Explains Long-Context Factuality

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T05:19:30.093604Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94bf6f2b-6176-4f0c-922b-f484219d0d79 · inbound

From Concepts to Components: Concept-Agnostic Attention Module Discovery in Transformers cites this paper.

From Concepts to Components: Concept-Agnostic Attention Module Discovery in Transformers Retrieval Head Mechanistically Explains Long-Context Factuality

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-15T19:17:52.481918Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e426f948-c613-43ec-8792-f1c531e4f856 · inbound

Soft Head Selection for Injecting ICL-Derived Task Embeddings cites this paper.

Soft Head Selection for Injecting ICL-Derived Task Embeddings Retrieval Head Mechanistically Explains Long-Context Factuality

Reference 21

Resolution: verified exact; arxiv_id, observed 2026-05-19T02:41:59.760276Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 37b53a26-9c28-44aa-b1c1-4b7b86c08fa2 · inbound

Which Heads Matter for Reasoning? RL-Guided KV Cache Compression cites this paper.

Which Heads Matter for Reasoning? RL-Guided KV Cache Compression Retrieval Head Mechanistically Explains Long-Context Factuality

Reference 1996

Resolution: unresolved; no resolver link, observed 2026-08-04T10:50:10.696555Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40b49129-f577-47ca-9319-2c48cba3e381 · inbound

BLASST: Dynamic BLocked Attention Sparsity via Softmax Thresholding cites this paper.

BLASST: Dynamic BLocked Attention Sparsity via Softmax Thresholding Retrieval Head Mechanistically Explains Long-Context Factuality

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-05-16T22:21:18.643653Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 0f6073a3-80ac-45c4-a703-1a5a745be248 · inbound

RAT+: Train Dense, Infer Sparse -- Recurrence Augmented Attention for Dilated Inference cites this paper.

RAT+: Train Dense, Infer Sparse -- Recurrence Augmented Attention for Dilated Inference Retrieval Head Mechanistically Explains Long-Context Factuality

Reference 30

Resolution: verified exact; arxiv_id, observed 2026-05-15T21:00:17.924977Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 8670b514-1a85-49a2-834f-e3d601c544c2 · inbound

RAT+: Train Dense, Infer Sparse -- Recurrence Augmented Attention for Dilated Inference cites this paper.

RAT+: Train Dense, Infer Sparse -- Recurrence Augmented Attention for Dilated Inference Retrieval Head Mechanistically Explains Long-Context Factuality

Reference 30

Resolution: verified exact; arxiv_id, observed 2026-05-21T12:50:09.515334Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation e30a9bc2-9ed5-477d-bc72-74b9468cd27e · inbound

RAT+: Train Dense, Infer Sparse -- Recurrence Augmented Attention for Dilated Inference cites this paper.

RAT+: Train Dense, Infer Sparse -- Recurrence Augmented Attention for Dilated Inference Retrieval Head Mechanistically Explains Long-Context Factuality

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-02T22:05:43.047950Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation da03d3dc-8ccb-4d84-9f9a-57d58a16e110 · inbound

Are Finer Citations Always Better? Rethinking Granularity for Attributed Generation cites this paper.

Are Finer Citations Always Better? Rethinking Granularity for Attributed Generation Retrieval Head Mechanistically Explains Long-Context Factuality

Reference 3

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T22:18:20.956733Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation f09ae757-7ccc-4261-ad6c-213ca538b80f · inbound

ART: Attention Replacement Technique to Improve Factuality in LLMs cites this paper.

ART: Attention Replacement Technique to Improve Factuality in LLMs Retrieval Head Mechanistically Explains Long-Context Factuality

Reference 10

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T22:30:51.013361Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation d6282e81-555f-473f-8ae6-b95b4a034277 · inbound

Flux Attention: Context-Aware Hybrid Attention for Efficient LLMs Inference cites this paper.

Flux Attention: Context-Aware Hybrid Attention for Efficient LLMs Inference Retrieval Head Mechanistically Explains Long-Context Factuality

Reference 43

Resolution: verified exact; arxiv_id, observed 2026-05-11T06:25:58.282169Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 8c3d063c-82c7-4918-89f1-b4a0aea98836 · inbound

One Token per Highly Selective Frame: Towards Extreme Compression for Long Video Understanding cites this paper.

One Token per Highly Selective Frame: Towards Extreme Compression for Long Video Understanding Retrieval Head Mechanistically Explains Long-Context Factuality

Reference 66

Resolution: verified exact; arxiv_id, observed 2026-05-10T13:30:26.603104Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 8d25a5de-e80b-47cb-860f-946a24b502a2 · inbound

SAGE: Selective Attention-Guided Extraction for Token-Efficient Document Indexing cites this paper.

SAGE: Selective Attention-Guided Extraction for Token-Efficient Document Indexing Retrieval Head Mechanistically Explains Long-Context Factuality

Reference 46

Resolution: verified exact; arxiv_id, observed 2026-05-10T08:32:52.110230Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 0ed7fb54-ca73-439d-a957-4479188e25cf · inbound

Adversarial Humanities Benchmark: Results on Stylistic Robustness in Frontier Model Safety cites this paper.

Adversarial Humanities Benchmark: Results on Stylistic Robustness in Frontier Model Safety Retrieval Head Mechanistically Explains Long-Context Factuality

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-05-11T12:01:06.406908Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 1055c95e-54cc-4e24-b24e-756ec2155e0b · inbound

Understanding the Mechanism of Altruism in Large Language Models cites this paper.

Understanding the Mechanism of Altruism in Large Language Models Retrieval Head Mechanistically Explains Long-Context Factuality

Reference 195

Resolution: verified exact; arxiv_id, observed 2026-05-11T13:31:02.448419Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation c14dbce6-0a15-41f3-a058-74b3f556c46f · inbound

CAST: Mitigating Object Hallucination in Large Vision-Language Models via Caption-Guided Visual Attention Steering cites this paper.

CAST: Mitigating Object Hallucination in Large Vision-Language Models via Caption-Guided Visual Attention Steering Retrieval Head Mechanistically Explains Long-Context Factuality

Reference 62

Resolution: verified exact; arxiv_id, observed 2026-05-09T06:50:40.179491Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 83011307-5a74-4abf-ab28-ff105b72adb2 · inbound

AB-Sparse: Sparse Attention with Adaptive Block Size for Accurate and Efficient Long-Context Inference cites this paper.

AB-Sparse: Sparse Attention with Adaptive Block Size for Accurate and Efficient Long-Context Inference Retrieval Head Mechanistically Explains Long-Context Factuality

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-05-13T05:12:18.446385Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation d8d90c2d-d30f-4d4d-8a53-71606842e9df · inbound

The Readout Shortcut: Positional Number Copying Dominates Arithmetic CoT Readout in Small Language Models cites this paper.

The Readout Shortcut: Positional Number Copying Dominates Arithmetic CoT Readout in Small Language Models Retrieval Head Mechanistically Explains Long-Context Factuality

Reference 38

Resolution: verified exact; arxiv_id, observed 2026-05-25T06:30:25.619495Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 2c8dc8f6-514e-491e-a5cc-c4b3afe071fb · inbound

Give it Space! Explicit Disentangling of Positional and Semantic Representations in Encoders cites this paper.

Give it Space! Explicit Disentangling of Positional and Semantic Representations in Encoders Retrieval Head Mechanistically Explains Long-Context Factuality

Reference 34

Resolution: verified exact; arxiv_id, observed 2026-06-29T07:33:13.059096Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation f2f2ecda-b1a0-4497-b7eb-70bd75739a51 · inbound

Hallucinations as Orthogonal Noise: Inference-Time Manifold Alignment via Dynamic Contextual Orthogonalization cites this paper.

Hallucinations as Orthogonal Noise: Inference-Time Manifold Alignment via Dynamic Contextual Orthogonalization Retrieval Head Mechanistically Explains Long-Context Factuality

Reference 76

Resolution: verified exact; arxiv_id, observed 2026-07-02T02:36:26.239126Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation b5dea5f8-61dd-47d1-86ba-6575ac55a39e · inbound

Characterize Then Distill: Mechanistic Reasoning in Large Output Spaces cites this paper.

Characterize Then Distill: Mechanistic Reasoning in Large Output Spaces Retrieval Head Mechanistically Explains Long-Context Factuality

Reference 42

Resolution: verified exact; arxiv_id, observed 2026-06-27T22:31:21.405693Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 4dd60dff-879d-4cbb-ab59-61ae2c9dec4d · inbound

Reroute, Don't Remove: Recoverable Visual Token Routing for Vision-Language Models cites this paper.

Reroute, Don't Remove: Recoverable Visual Token Routing for Vision-Language Models Retrieval Head Mechanistically Explains Long-Context Factuality

Reference 68

Resolution: verified exact; arxiv_id, observed 2026-07-03T11:28:04.132960Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation a2f1f760-524a-4b8b-aacc-c98f9b257fe3 · inbound

Plans Don't Persist: Why Context Management Is Load Bearing for LLM Agents cites this paper.

Plans Don't Persist: Why Context Management Is Load Bearing for LLM Agents Retrieval Head Mechanistically Explains Long-Context Factuality

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-07-04T10:49:46.413877Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 94232f49-3bdb-4648-a9d6-d62cbc59f373 · inbound

The Hitchhiker's Guide to Agentic AI: From Foundations to Systems cites this paper.

The Hitchhiker's Guide to Agentic AI: From Foundations to Systems Retrieval Head Mechanistically Explains Long-Context Factuality

Reference 76

Resolution: verified exact; arxiv_id, observed 2026-07-04T11:09:46.556408Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 488de992-fa8f-4a7a-b428-880c866322af · inbound

The Hitchhiker's Guide to Agentic AI: From Foundations to Systems cites this paper.

The Hitchhiker's Guide to Agentic AI: From Foundations to Systems Retrieval Head Mechanistically Explains Long-Context Factuality

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-02T10:27:16.360917Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 865b57c6-8a11-46fb-8b50-4e3da91df5f2 · inbound

RaBitQCache: Rotated Binary Quantization for KVCache in Long Context LLM Inference cites this paper.

RaBitQCache: Rotated Binary Quantization for KVCache in Long Context LLM Inference Retrieval Head Mechanistically Explains Long-Context Factuality

Reference 31

Resolution: verified exact; arxiv_id, observed 2026-07-01T06:35:29.424849Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 1b32c996-6318-4062-9b9c-0358ed8abc64 · inbound

Can Language Models Actually Retrieve In-Context? Drowning in Documents at Million Token Scale cites this paper.

Can Language Models Actually Retrieve In-Context? Drowning in Documents at Million Token Scale Retrieval Head Mechanistically Explains Long-Context Factuality

Reference 40

Resolution: verified exact; arxiv_id, observed 2026-07-03T20:48:55.237547Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation f2d88a32-13a5-4015-86b9-0447b7c05495 · inbound

Does Bielik Know What It Doesn't Know? Activation Dispersion Separates Entity Familiarity from Factual Reliability Across Model Scale cites this paper.

Does Bielik Know What It Doesn't Know? Activation Dispersion Separates Entity Familiarity from Factual Reliability Across Model Scale Retrieval Head Mechanistically Explains Long-Context Factuality

Reference 37

Resolution: metadata mismatch; local_arxiv, observed 2026-07-10T18:27:31.299442Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation ed5e8f83-7d83-4651-8cf3-9fea53745609 · inbound

One mechanism for many mental spaces: a shared router over a value slot in language models cites this paper.

One mechanism for many mental spaces: a shared router over a value slot in language models Retrieval Head Mechanistically Explains Long-Context Factuality

Reference 9

Resolution: unresolved; no resolver link, observed 2026-07-14T13:13:40.183633Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 16a6c4a1-837a-4788-9142-b4b3a08abc3e · inbound

One mechanism for many mental spaces: a shared router over a value slot in language models cites this paper.

One mechanism for many mental spaces: a shared router over a value slot in language models Retrieval Head Mechanistically Explains Long-Context Factuality

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-02T07:26:55.925100Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c2c9e142-0198-4fa5-88bd-1e5772c2407a · inbound

Belief-reality separation lives in routing over a shared value slot in language models cites this paper.

Belief-reality separation lives in routing over a shared value slot in language models Retrieval Head Mechanistically Explains Long-Context Factuality

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-02T07:25:57.491651Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4cf497b2-3425-430b-b6a9-f74192599822 · inbound

Adaptive Filtering of the KV Cache: Diagnosing and Correcting Structural-Role Bias in LLM Inference cites this paper.

Adaptive Filtering of the KV Cache: Diagnosing and Correcting Structural-Role Bias in LLM Inference Retrieval Head Mechanistically Explains Long-Context Factuality

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:46.900228Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c5fcd489-85bd-4766-82cb-123fdc3d0930 · inbound

Graded Entity-Familiarity Readouts in Language Models: Polish Adaptation, Cross-Language Robustness, and Refusal Steering cites this paper.

Graded Entity-Familiarity Readouts in Language Models: Polish Adaptation, Cross-Language Robustness, and Refusal Steering Retrieval Head Mechanistically Explains Long-Context Factuality

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-02T04:52:42.981569Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e853122-4872-4cac-bba1-ae0c2a867d0b · inbound

Learning What Matters: Supervising Global Context Pruning with Causal Evidence Sets cites this paper.

Learning What Matters: Supervising Global Context Pruning with Causal Evidence Sets Retrieval Head Mechanistically Explains Long-Context Factuality

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-01T07:14:37.993046Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 756c2e08-dfb1-4ea4-8065-39a27f4b7eff · inbound

HALT: Verification-Aware Stopping for Retrieval-Augmented Search Agents cites this paper.

HALT: Verification-Aware Stopping for Retrieval-Augmented Search Agents Retrieval Head Mechanistically Explains Long-Context Factuality

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-04T16:52:13.962789Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0b671abe-cb60-4528-ab6d-ba4e4235f9f4 · inbound

HALT: Verification-Aware Stopping for Retrieval-Augmented Search Agents cites this paper.

HALT: Verification-Aware Stopping for Retrieval-Augmented Search Agents Retrieval Head Mechanistically Explains Long-Context Factuality

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-07T00:16:07.269256Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f75ee32-cdc5-4134-9f55-3ba29a10b08b · inbound

PhyCheck: Fine-Grained Evidence-Grounded Dataset for Physical Law Understanding in Video-LLMs cites this paper.

PhyCheck: Fine-Grained Evidence-Grounded Dataset for Physical Law Understanding in Video-LLMs Retrieval Head Mechanistically Explains Long-Context Factuality

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-04T13:43:52.718558Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58fc737b-3209-4016-90b0-cd5b545cbf89 · inbound

PhyCheck: Fine-Grained Evidence-Grounded Dataset for Physical Law Understanding in Video-LLMs cites this paper.

PhyCheck: Fine-Grained Evidence-Grounded Dataset for Physical Law Understanding in Video-LLMs Retrieval Head Mechanistically Explains Long-Context Factuality

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T00:11:48.860067Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e5d1988-2bef-48a6-9b2f-af5cc683a795 · inbound

Towards Efficient Reasoning in LLM-Based Recommender Systems via Model Merging cites this paper.

Towards Efficient Reasoning in LLM-Based Recommender Systems via Model Merging Retrieval Head Mechanistically Explains Long-Context Factuality

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-15T14:24:17.162708Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers