The Override Gap: A Magnitude Account of Knowledge Conflict Failure in Hypernetwork-Based Instant LLM Adaptation

• URL: http://arxiv.org/abs/2604.23750v1
• Date: Sun, 26 Apr 2026 14:59:14 GMT
• Title: The Override Gap: A Magnitude Account of Knowledge Conflict Failure in Hypernetwork-Based Instant LLM Adaptation
• Abstract summary: Hypernetwork-based methods internalize a document into an LLM's weights in a single forward pass.<n>When the document contradicts pretraining knowledge, accuracy collapses to 46.4% on the deepest facts.<n>We show the failure is a magnitude problem rather than a representational one.
• Score: 6.290180827867576
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Hypernetwork-based methods such as Doc-to-LoRA internalize a document into an LLM's weights in a single forward pass, but they fail systematically on conflicts: when the document contradicts pretraining knowledge, accuracy collapses to 46.4% on the deepest facts. We show the failure is a magnitude problem rather than a representational one. The hypernetwork already targets the right layers, but its adapter margin is approximately constant across documents while the pretrained margin grows with training frequency, so deep conflicts lose by construction. The account predicts that failure should track prior strength: sorting 194 conflicts by the base model's log-probability on the contradicted fact, baseline accuracy falls from 68% on weak-prior questions to 16% on strong-prior ones, a 52 percentage-point gap. The cure is amplitude. Selective Layer Boosting scales the adapter at its top-norm layers, and Conflict-Aware Internalization triggers boosting only when the base model is confident. Both are training-free; together they raise deep-conflict accuracy from 46.4% to 71.0% on Gemma-2B and from 53.6% to 72.5% on Mistral-7B while preserving novel-knowledge recall, and beat vanilla retrieval-augmented generation on medium conflicts by 18 percentage points despite operating entirely in parameter space. We release KID-Bench, a 489-question benchmark that separates novel recall, cross-knowledge combination, and prior-graded conflicts.

Related papers

• LLMs Can Predict Failure Risk, But Struggle to Predict Which Collaboration Protocol Pays Off: Cost-Aware Protocol Routing Across Reasoning Tasks [3.789882665982407]
  Multi-agent large language model (LLM) systems can improve reasoning by spending more computation.<n>We isolate this decision by running every problem under four protocols while holding the solver fixed within each setting.
  arXiv  Detail & Related papers  (2026-08-14T22:35:37Z)
• Share the Judge, Learn the Deferral: Where Specialization Helps LLM Evaluation [0.1269104766024433]
  We study 99,952 public, rubric-conditioned examples.<n>Supplying the correct rubric improves locked-test accuracy by 2.11 points over a response-only control.<n>On RewardBench 2, learned correctness heads route examples through a 0.6B-4B-8B cascade without changing any reward score.
  arXiv  Detail & Related papers  (2026-07-30T10:29:22Z)
• Data Quality over Capacity: Internalizing Documents into LoRA Adapters for Closed-Book QA [0.0]
  We study baking documents directly into the weights of a 4-bit Gemma-4-e4b model via LoRA.<n>We find that once adapter capacity is adequate, training-data quality is the dominant lever on closed-book accuracy.
  arXiv  Detail & Related papers  (2026-07-23T23:14:59Z)
• SkillDAG: Self-Evolving Typed Skill Graphs for LLM Skill Selection at Scale [54.70985426016736]
  We present SkillDAG, which models inter-skill relationships as a typed directed graph.<n>Each search returns vector matches, typed-edge neighbors, and conflict signals, and a propose-then-commit protocol lets the agent register execution-backed edges.<n>On ALFWorld and SkillsBench with MiniMax-M2.7, SkillDAG reaches 67.1% success and 27.3% reward.
  arXiv  Detail & Related papers  (2026-06-02T02:45:21Z)
• Not Just RLHF: Why Alignment Alone Won't Fix Multi-Agent Sycophancy [0.7212939068975618]
  We find that pretrained base models exhibit the same substitution pattern as their Instruct variants, averaging higher yield than Instruct.<n> patching above this window restores 96% of the clean-to-pressured P(correct) gap.<n>Two converging activation-space interventions show that pressure suppresses clean-reasoning features rather than activating a new sycophancy circuit.
  arXiv  Detail & Related papers  (2026-05-13T04:45:08Z)
• To Fuse or to Drop? Dual-Path Learning for Resolving Modality Conflicts in Multimodal Emotion Recognition [87.22988227382329]
  Multimodal emotion recognition (MER) benefits from combining text, audio, and vision, yet standard fusion often fails when modalities conflict.<n>We propose Dual-Path Conflict Resolution (DCR), a unified framework that learns when to fuse and when to drop modalities.
  arXiv  Detail & Related papers  (2026-05-06T13:11:33Z)
• Scalable Multi-Task Low-Rank Model Adaptation [43.22544779625565]
  Scaling multi-task low-rank adaptation (LoRA) to a large number of tasks induces catastrophic performance degradation.<n>We find that existing solutions, like regularization and dynamic routing, fail at scale because they are constrained by a fundamental trade-off.<n>We propose mtLoRA, a scalable solution with three novel designs.
  arXiv  Detail & Related papers  (2026-03-02T06:57:11Z)
• EdgeJury: Cross-Reviewed Small-Model Ensembles for Truthful Question Answering on Serverless Edge Inference [0.0]
  We present EdgeJury, a lightweight ensemble framework that improves truthfulness and robustness.<n>On TruthfulQA (MC1), EdgeJury achieves 76.2% accuracy.<n>On a 200-question adversarial EdgeCases set, EdgeJury yields +48.2% relative gains.
  arXiv  Detail & Related papers  (2025-12-29T14:48:40Z)
• That's Deprecated! Understanding, Detecting, and Steering Knowledge Conflicts in Language Models for Code Generation [55.78914774437411]
  Large language models (LLMs) behave when faced with discrepancies between their parametric knowledge and conflicting information contained in a prompt.<n>We propose a domain-agnostic framework for constructing and interpreting such conflicts.<n>We show that activation-level steering can achieve up to a textbf12.6% improvement in steering success over a random baseline.
  arXiv  Detail & Related papers  (2025-10-21T22:27:56Z)
• CLUE: Non-parametric Verification from Experience via Hidden-State Clustering [64.50919789875233]
  We show that correctness of a solution is encoded as a geometrically separable signature within the trajectory of hidden activations.<n>ClUE consistently outperforms LLM-as-a-judge baselines and matches or exceeds modern confidence-based methods in reranking candidates.
  arXiv  Detail & Related papers  (2025-10-02T02:14:33Z)
• Retrieval-Augmented Generation with Conflicting Evidence [57.66282463340297]
  Large language model (LLM) agents are increasingly employing retrieval-augmented generation (RAG) to improve the factuality of their responses.<n>In practice, these systems often need to handle ambiguous user queries and potentially conflicting information from multiple sources.<n>We propose RAMDocs (Retrieval with Ambiguity and Misinformation in Documents), a new dataset that simulates complex and realistic scenarios for conflicting evidence for a user query.
  arXiv  Detail & Related papers  (2025-04-17T16:46:11Z)
• AdaCAD: Adaptively Decoding to Balance Conflicts between Contextual and Parametric Knowledge [57.66282463340297]
  Knowledge conflict arises from discrepancies between information in the context of a large language model and the knowledge stored in its parameters.<n>We propose a fine-grained, instance-level approach called AdaCAD, which dynamically infers the weight of adjustment based on the degree of conflict.<n>We show that ADACAD consistently outperforms other decoding baselines with average QA accuracy gains of 14.21% (absolute) over a static contrastive baseline, and improves the factuality of summaries by 6.19 (AlignScore)
  arXiv  Detail & Related papers  (2024-09-11T16:35:18Z)
• Certified Robust Accuracy of Neural Networks Are Bounded due to Bayes Errors [3.350980549219263]
  certified training improves robustness but also decreases accuracy noticeably. It is not clear whether there is a certain fundamental limit on achieving robustness whilst maintaining accuracy. By adopting Bayes error to robustness analysis, we investigate the limit of certified robust accuracy.
  arXiv  Detail & Related papers  (2024-05-19T13:23:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.