mlsanityData to 14 Oct 2026

GRIP: Grounded Reasoning via Information-Restricted Premises

arXiv 2608.16776 ↗First posted 17 Aug 2026cs.AIcited by 0

On the map: Retrieval-augmented generation → RAG robustness and adaptive retrieval

Abstract (arXiv)

High-capacity encoders in retrieval-augmented generation (RAG) can let the query dominate the latent state, leaving retrieved evidence functionally irrelevant. We call this failure mode query dominance. To address it, we introduce GRIP (Grounded Reasoning via Information-Restricted Premises), which imposes capacity asymmetry: the decoder keeps full-dimensional access to the query, while retrieved evidence passes through a severe stochastic bottleneck. This forces the evidence channel to encode only the residual information unavailable from the query. Across five reasoning benchmarks, GRIP outperforms strong iterative baselines, cuts a query--latent mutual-information diagnostic by roughly 30× (14.8 → 0.47 bits), and reduces hallucination by 73%. Residual-alignment analysis further shows that the bottleneck output occupies subspaces less aligned with the query than baseline representations.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RAG robustness and adaptive retrieval, one of 15 directions in Retrieval-augmented generation. Builds on 23 of its 25 references that are in the map. First posted on arXiv 17 Aug 2026.

Builds on

23 of 25 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025Accommodate Knowledge Conflicts in Retrieval-augmented LLMs: Towards Robust Response Generation in the Wild17 Apr
  2. 2024Sufficient Context: A New Lens on Retrieval Augmented Generation Systems9 Nov
  3. 2024MiniCheck: Efficient Fact-Checking of LLMs on Grounding Documents16 Apr
  4. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection17 Oct

Other references · 19

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  3. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  4. 2020Shortcut Learning in Deep Neural Networkscited by 1,969
  5. 2018Know What You Don't Know: Unanswerable Questions for SQuADcited by 1,554
  6. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,282
  7. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 1,128
  8. 2022Measuring and Narrowing the Compositionality Gap in Language Modelscited by 1,075
  9. 2019How Contextual are Contextualized Word Representations? Comparing the Geometry of BERT, ELMo, and GPT-2 Embeddingscited by 784
  10. 2021Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategiescited by 743
  11. 2023Making Retrieval-Augmented Language Models Robust to Irrelevant Contextcited by 369
  12. 2023Trusting Your Evidence: Hallucinate Less with Context-aware Decodingcited by 327
7 more
  1. 2020ProofWriter: Generating Implications, Proofs, and Abductive Statements over Natural Languagecited by 324
  2. 2020CLUB: A Contrastive Log-ratio Upper Bound of Mutual Informationcited by 235
  3. 2017Emergence of Invariance and Disentanglement in Deep Representationscited by 215
  4. 2019Understanding the Limitations of Variational Mutual Information Estimatorscited by 140
  5. 2024Context-DPO: Aligning Language Models for Context-Faithfulnesscited by 50
  6. 2023Beyond Normal: On the Evaluation of Mutual Information Estimatorscited by 37
  7. 2024An Information Bottleneck Perspective for Effective Noise Filtering on Retrieval-Augmented Generationcited by 16

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Rethinking the Reranker: Boundary-Aware Evidence Selection for Robust Retrieval-Augmented Generation
  2. 2026Skill-RAG: Failure-State-Aware Retrieval Augmentation via Hidden-State Probing and Skill Routing
  3. 2026Retrieval-Infused Reasoning Sandbox: A Benchmark for Decoupling Retrieval and Reasoning Capabilities
  4. 2026DynaKRAG: A Unified Framework for Learnable Evidence Control in Multi-Hop Retrieval-Augmented Generation
  5. 2026Grounded Decoding: Retrieval-Anchored Probability Fusion for Faithful RAG
  6. 2026PruneRAG: Confidence-Guided Query Decomposition Trees for Efficient Retrieval-Augmented Generation
  7. 2025Retrieval as a Decision: Training-Free Adaptive Gating for Efficient RAG
  8. 2025Beyond RAG: Task-Aware KV Cache Compression for Comprehensive Knowledge Reasoning