KARMA: Knowledge graph-based Automated Reasoning Materialization and Alignment

• URL: http://arxiv.org/abs/2607.03166v1
• Date: Fri, 03 Jul 2026 10:06:40 GMT
• Title: KARMA: Knowledge graph-based Automated Reasoning Materialization and Alignment
• Abstract summary: template-based contrastive synthesis is scalable, but its candidates differ only in a few entity-slots.<n>We formalize this as the Resolution Mismatch Problem and propose KARMA.<n>It enumerates schema-constrained paths over domain knowledge graphs and verbalizes them into slot-aligned contrastive candidates.
• Score: 1.0323063834827415
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Template-based contrastive synthesis is scalable, but its candidates often differ only in a few entity-slots while sequence-level optimization spreads supervision over mostly shared templates. We formalize this as the Resolution Mismatch Problem and propose KARMA, which enumerates schema-constrained paths over domain knowledge graphs and verbalizes them into slot-aligned contrastive candidates. Slot-Parallel Alignment (SPA) then applies a decoupled slot-level objective to route preference supervision to discriminative entity-slots, with slot-aware masked attention serving as an optional packed-evaluation implementation. Across biomedical, computer-science, and chemistry benchmarks, KARMA outperforms base LLM and same-data SFT baselines, and compares favorably with sequence and token-level preference methods.

Related papers

• Rethink MAE with Linear Time-Invariant Dynamics [0.0]
  We show that token order is a critical, exploitable dimension in frozen visual representations.<n>We propose SSMProbe, a probing framework driven by a State Space Model.
  arXiv  Detail & Related papers  (2026-04-29T15:07:00Z)
• Self-Organizing Maps with Optimized Latent Positions [0.0]
  We propose an objective-based topographic mapping method that introduces a continuous latent position for each data point.<n>Experiments on a synthetic saddle manifold, scalability studies on the Digits and MNIST datasets, and 16 benchmark datasets show that SOM-OLP achieves competitive neighborhood preservation and quantization performance.
  arXiv  Detail & Related papers  (2026-04-15T08:42:49Z)
• TAB-PO: Preference Optimization with a Token-Level Adaptive Barrier for Token-Critical Structured Generation [0.0]
  Token-weighted, reference-adjusted advantages that prioritize high-value semantic tokens are presented.<n>We evaluate TAB-PO on medical communication annotation.
  arXiv  Detail & Related papers  (2026-02-03T23:48:13Z)
• LLM-Guided Exemplar Selection for Few-Shot Wearable-Sensor Human Activity Recognition [1.575769267908841]
  We propose an LLM-Guided Exemplar Selection framework to address a key limitation in state-of-the-art Human Activity Recognition (HAR) methods.<n>Our method incorporates semantic reasoning via an LLM-generated knowledge prior that captures feature importance, inter-class confusability, and exemplar budget multipliers.<n>The framework achieves a macro F1-score of 88.78%, outperforming classical approaches such as random sampling, herding, and k-center.
  arXiv  Detail & Related papers  (2025-12-26T21:03:15Z)
• GEM: Generative Entropy-Guided Preference Modeling for Few-shot Alignment of LLMs [5.1816417820270075]
  In this paper, we propose a generative entropy-guided preference modeling approach named GEM for large language models (LLMs)<n>Instead of training a discriminative reward model on preference data, we directly train the LLM to internalize a closed-loop optimization architecture.<n> Experiments on general benchmarks and domain-specific tasks demonstrate that our GEM achieves significant improvements with few-shot preference data.
  arXiv  Detail & Related papers  (2025-11-17T06:04:47Z)
• Unsupervised Conformal Inference: Bootstrapping and Alignment to Control LLM Uncertainty [49.19257648205146]
  We propose an unsupervised conformal inference framework for generation.<n>Our gates achieve close-to-nominal coverage and provide tighter, more stable thresholds than split UCP.<n>The result is a label-free, API-compatible gate for test-time filtering.
  arXiv  Detail & Related papers  (2025-09-26T23:40:47Z)
• In-context Ranking Preference Optimization [65.5489745857577]
  We propose an In-context Ranking Preference Optimization (IRPO) framework to optimize large language models (LLMs) based on ranking lists constructed during inference.<n>We show IRPO outperforms standard DPO approaches in ranking performance, highlighting its effectiveness in aligning LLMs with direct in-context ranking preferences.
  arXiv  Detail & Related papers  (2025-04-21T23:06:12Z)
• RankMatch: A Novel Approach to Semi-Supervised Label Distribution Learning Leveraging Inter-label Correlations [52.549807652527306]
  This paper introduces RankMatch, an innovative approach for Semi-Supervised Label Distribution Learning (SSLDL) RankMatch effectively utilizes a small number of labeled examples in conjunction with a larger quantity of unlabeled data. We establish a theoretical generalization bound for RankMatch, and through extensive experiments, demonstrate its superiority in performance against existing SSLDL methods.
  arXiv  Detail & Related papers  (2023-12-11T12:47:29Z)
• ProTeCt: Prompt Tuning for Taxonomic Open Set Classification [59.59442518849203]
  Few-shot adaptation methods do not fare well in the taxonomic open set (TOS) setting. We propose a prompt tuning technique that calibrates the hierarchical consistency of model predictions. A new Prompt Tuning for Hierarchical Consistency (ProTeCt) technique is then proposed to calibrate classification across label set granularities.
  arXiv  Detail & Related papers  (2023-06-04T02:55:25Z)
• Large-Scale Sequential Learning for Recommender and Engineering Systems [91.3755431537592]
  In this thesis, we focus on the design of an automatic algorithms that provide personalized ranking by adapting to the current conditions. For the former, we propose novel algorithm called SAROS that take into account both kinds of feedback for learning over the sequence of interactions. The proposed idea of taking into account the neighbour lines shows statistically significant results in comparison with the initial approach for faults detection in power grid.
  arXiv  Detail & Related papers  (2022-05-13T21:09:41Z)
• Bayesian Attention Modules [65.52970388117923]
  We propose a scalable version of attention that is easy to implement and optimize. Our experiments show the proposed method brings consistent improvements over the corresponding baselines.
  arXiv  Detail & Related papers  (2020-10-20T20:30:55Z)

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.