DiagLoop: A Counterfactual Data Flywheel with Stage-Localized Reinforcement for Diagnostic LLMs

• URL: http://arxiv.org/abs/2608.03674v1
• Date: Tue, 04 Aug 2026 13:49:41 GMT
• Title: DiagLoop: A Counterfactual Data Flywheel with Stage-Localized Reinforcement for Diagnostic LLMs
• Abstract summary: We present DiagLoop, a counterfactual data flywheel that converts codified physical relations or clinical guidelines into training supervision.<n>A training-only teacher proposes counterfactual worlds by varying causes, contexts, and observations, while an independent hybrid checker admits only valid worlds.<n>For nonterminal failures, a bounded repair probes downstream competence, and the resulting weakness profile guides subsequent data generation.
• Score: 5.241146164724621
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Causal diagnostic models must explain how conclusions follow from evidence because diagnoses guide repairs and treatments. Yet serious cases are scarce, records rarely contain reasoning paths, and data transfer poorly across configurations, complicating local deployment. We present DiagLoop, a counterfactual data flywheel that converts codified physical relations or clinical guidelines, authored once per mechanism family, into training supervision beyond recorded cases. A training-only teacher proposes counterfactual worlds by varying causes, contexts, and observations, while an independent hybrid checker admits only valid worlds. The student reasons through symptom abstraction, causal-chain construction, and root-cause attribution. Stage-specific criteria identify its earliest failure. For nonterminal failures, a bounded repair probes downstream competence, and the resulting weakness profile guides subsequent data generation. Stage-localized reinforcement learning updates only the model-generated continuation, while replay and preservation reduce forgetting. The same criteria govern admission, attribution, reward, and regeneration through checks separate from the proposer. Using only synthesized scenarios and no case-level expert reasoning annotations, the resulting 8B model improves strict path correctness over the strongest conventional baseline. Gains are 11.6 points across eight industrial systems and 5.5 points across ten disease categories. Gains over a deranged-routing control are 3.9 and 2.3 points, respectively. The model also exceeds the evaluated proprietary references in both domains, even when they receive few-shot examples or the specification in context.

Related papers

• SynthSentry: Detecting Synthetic Data Contamination in Language Model Training Data [2.998247765202193]
  We introduce a corpus-level, model-agnostic contamination signal requiring no access to the generating model, no generation history, and no synthetic labels.<n>We evaluate on corpora contaminated by small open-weight generators and an instruction-tuned open-weight model under a leave-one-generator-out protocol.<n>The score ranks corpora by severity with little loss when whole generator families are held out.
  arXiv  Detail & Related papers  (2026-09-11T02:25:18Z)
• Vision: Data-Centric Anchoring for Robust and Interpretable Agentic AI [21.406298170489507]
  We argue that robustness and interpretability should be engineered into the data environment, not extracted from models after training.<n>Our central contribution is the Data-Centric Agentic Loop, a four-stage framework of Curate, Augment, Constrain, and Attribute.<n>We ground the framework in a failure-driven taxonomy that links four core failure modes to the data lifecycle.
  arXiv  Detail & Related papers  (2026-09-08T03:57:54Z)
• From Trajectories to Evidence: Auditable Experimental Records for Industrial Research Agents [47.678562263387214]
  Research agents increasingly conduct multi-round machine-learning experiments in industrial recommendation settings.<n>Yet a completed trajectory is not automatically evidence: generated artifacts may be unsupported or incomplete, executed rounds may be invalid or confounded, and later modifications may obscure earlier findings.<n>We introduce an evidence-grounded framework that couples bounded verification of consequential artifacts with post-execution claim qualification.
  arXiv  Detail & Related papers  (2026-08-05T13:37:38Z)
• CausalOPD: First-Wrong-Step Supervision for Distilling Causal Chain Reasoning [5.241146164724621]
  CausalOPD is a curriculum online process distillation framework.<n>A knowledge-augmented teacher first provides trajectories grounded in domain-specific causal rules.<n>A causal-stage curriculum advances from evidence-level to mechanism-level and conclusion-level errors.
  arXiv  Detail & Related papers  (2026-08-04T13:49:12Z)
• Conformalized Large Language Models under Configuration Shift [46.502741608809174]
  Conformal prediction is a distribution-free framework for uncertainty quantification.<n>Nonconformity scores are often induced by an inference pipeline, not just a fixed model.<n>We show that configuration shift consistently erodes CP validity.
  arXiv  Detail & Related papers  (2026-08-02T19:34:41Z)
• Before the Action: Benchmarking LLMs on Prospective Hypothesis Discovery [95.44432473367836]
  Large language models (LLMs) excel at answering pre-specified questions, yet their ability to navigate the open-ended, pre-conclusion stage of discovery remains largely unmeasured.<n>We introduce Prospective Hypothesis Discovery (PHD), which asks models to autonomously construct grounded, discnative, and testable hypothesis spaces from inconclusive evidence.<n>We introduce HypoArena, comprising HypoData, a benchmark of 988 cases across six scientific and analytical domains, and HypoEval, an evaluation framework for open-ended hypothesis sets.
  arXiv  Detail & Related papers  (2026-07-17T08:56:43Z)
• DriftScope: Measuring The Hidden Effects of Diffusion Model Adaptation [50.584834483403675]
  Adapting pre-trained text-to-image diffusion models, whether to learn new visual concepts or erase unwanted ones, is routinely evaluated on its intended effects alone.<n>We demonstrate that adaptation systematically damages semantically unrelated concepts in ways that aggregate metrics structurally cannot surface.<n>We introduce DriftScope, a prompt-level diagnostic tool that takes any two model checkpoints and returns a ranked list of tokens whose visual concepts have shifted most between them.
  arXiv  Detail & Related papers  (2026-06-30T20:57:51Z)
• One Reflection Is Not Enough: Self-Correcting Autonomous Research via Multi-Hypothesis Failure Attribution [85.65263343588026]
  We propose SAGE, a Self-correcting, Autonomous, Grounded Experimenter.<n>Its core mechanism, Multi-Hypothesis Failure Attribution (MHFA), treats recovery as a structured causal diagnosis.<n>On a 12-topic, 5-domain benchmark, SAGE increases metrics-bearing outputs from 42% to 92% over a baseline reflection.
  arXiv  Detail & Related papers  (2026-06-30T10:54:16Z)
• AuthTrace: Diagnosing Evidence Construction in Thematically Dense Single-Author Corpora [6.956097396264084]
  We introduce AuthTrace, a diagnostic benchmark built on thematically dense single-author corpora.<n>AuthTrace provides explicit quoted evidence, exact fan-in annotation, and a unified pack-level protocol measuring evidence recall, evidence precision, and answer correctness.
  arXiv  Detail & Related papers  (2026-05-25T03:10:52Z)
• SAAG: Structured Agent Assessment and Grounding [13.62148061055744]
  We propose a cascaded diagnostic framework that decomposes agent-calling evaluation into three sequential stages.<n>We evaluate this framework on a benchmark derived from Glaive's function-calling dataset across registry sizes of 5, 10, and 15 agents.
  arXiv  Detail & Related papers  (2026-04-30T19:33:58Z)
• CausalT5K: Diagnosing and Informing Refusal for Trustworthy Causal Reasoning of Skepticism, Sycophancy, Detection-Correction, and Rung Collapse [1.4608214000864057]
  CausalT5K is a diagnostic benchmark of over 5,000 cases across 10 domains.<n>Unlike synthetic benchmarks, CausalT5K embeds causal traps in realistic narratives.<n>Preliminary experiments reveal a Four-Quadrant Control Landscape where static audit policies universally fail.
  arXiv  Detail & Related papers  (2026-02-09T17:36:56Z)
• Decomposed Prompting Does Not Fix Knowledge Gaps, But Helps Models Say "I Don't Know" [47.930782177987446]
  Large language models often struggle to recognize their knowledge limits in closed-book question answering, leading to confident hallucinations.<n>We evaluate three task-equivalent prompting regimes: Direct, Assistive, and Incremental, across different model scales and multi-hop QA benchmarks.<n>Because factual knowledge is stable while hallucinations are agreement, cross-regime provides a precise signal of internal uncertainty.
  arXiv  Detail & Related papers  (2026-02-04T18:39:58Z)
• BURN: Backdoor Unlearning via Adversarial Boundary Analysis [73.14147934175604]
  Backdoor unlearning aims to remove backdoor-related information while preserving the model's original functionality.<n>We propose Backdoor Unlearning via adversaRial bouNdary analysis (BURN), a novel defense framework that integrates false correlation decoupling, progressive data refinement, and model purification.
  arXiv  Detail & Related papers  (2025-07-14T17:13:06Z)
• Robust Root Cause Diagnosis using In-Distribution Interventions [31.19149413954674]
  Diagnosing the root cause of an anomaly in a complex interconnected system is a pressing problem in today's cloud services and industrial operations.<n>We propose In-Distribution Interventions (IDI), a novel algorithm that predicts root cause as nodes that meet two criteria.
  arXiv  Detail & Related papers  (2025-05-02T00:19:43Z)
• DAGnosis: Localized Identification of Data Inconsistencies using Structures [73.39285449012255]
  Identification and appropriate handling of inconsistencies in data at deployment time is crucial to reliably use machine learning models. We use directed acyclic graphs (DAGs) to encode the training set's features probability distribution and independencies as a structure. Our method, called DAGnosis, leverages these structural interactions to bring valuable and insightful data-centric conclusions.
  arXiv  Detail & Related papers  (2024-02-26T11:29:16Z)

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.