ARIA: A Causal-Aware Framework for Rescuing LLM Reasoning in Trustworthy Materials Discovery

• URL: http://arxiv.org/abs/2606.22375v1
• Date: Sun, 21 Jun 2026 07:51:03 GMT
• Title: ARIA: A Causal-Aware Framework for Rescuing LLM Reasoning in Trustworthy Materials Discovery
• Abstract summary: We introduce ARIA, a causal-aware framework that conditions knowledge use on mechanistic completeness.<n>ARIA produces auditable causal traces, enabling physically grounded and trustworthy AI-assisted materials discovery.
• Score: 47.41577239591515
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Generative models have revolutionized the process of materials discovery, yet they often fail to satisfy underlying physical causality. Through an analysis of Large Language Models (LLMs) augmented with knowledge graphs derived from current literature, we uncover a phenomenon termed contextual tunneling, where models "over-anchor" on narrow, retrieved evidence while suppressing global physical reasoning. To address this problem, we introduce ARIA, a causal-aware framework that conditions knowledge use on mechanistic completeness. ARIA routes each query through a three-tier cascade: (i) direct causal reasoning when complete evidence chains of Process-Structure-Property (PSP) are available, (ii) physics-informed analogical transfer for sparse or novel material systems, and (iii) explicit parametric fallback when external evidence is incomplete. As a proof of concept, we construct a Knowledge Graph (KG) containing 2,839 extracted PSP relations from peer-reviewed articles in the materials literature and evaluate ARIA on forward prediction and inverse design tasks for two-dimensional (2D) materials. ARIA mitigates contextual tunneling, improves over unaugmented and naive KG-augmented baselines, and provides further gains when an online literature search is used for evidence enrichment. Crucially, ARIA produces auditable causal traces, enabling physically grounded and trustworthy AI-assisted materials discovery.

Related papers

• SAFE-G: Structure-aware Faithful Evidence-guided Generation for Knowledge-based Visual Question Answering [8.538563236020947]
  SAFE-G is a structure-Aware Faithful Evidence-guided Generation framework.<n>It enables precise evidence localization and trustworthy reasoning.<n>It outperforms prior methods by a margin of 8.9% and 3.5%.
  arXiv  Detail & Related papers  (2026-08-22T06:34:53Z)
• WILDTRACE: Benchmarking Natural Evidence Trails in Long-Context Reasoning [63.9071746889252]
  Answering complex questions over long documents frequently requires integrating evidence that the source itself disperses naturally across distant passages.<n>This source-internal evidence integration is central to real-world long-document analysis, yet existing benchmarks largely sidestep it.<n>We introduce WILDTRACE, a benchmark of 481 tasks over 214 naturally occurring long-form sources.
  arXiv  Detail & Related papers  (2026-07-10T12:09:21Z)
• ToE: A Hierarchical and Explainable Claim Verification Framework with Dynamic Multi-source Evidence Retrieval and Aggregation [23.934630478971517]
  ToE is a hierarchical evidence reasoning framework for automated fact-checking.<n>ToE integrates a reinforcement learning-driven multi-source retrieval agent, an evidence evaluation agent, and an argument tree aggregation algorithm.<n>We show that ToE achieves improvements ranging from 4 to 24 percentage points over competitive baselines.
  arXiv  Detail & Related papers  (2026-06-26T05:35:27Z)
• Skill-Contracted Agents for Evidence-Aware Materials Literature Analysis [8.055788977592144]
  Materials science literature analysis requires simultaneous attention to composition, processing, characterization, and property relationships.<n>Here we present AlphaAgent, a skill-driven agent framework that decouples retrieval-based question answering from paper-level report generation.<n>A dedicated skill rewrites user requests into material-specific intents, queries a curated index of more than 300,000 papers from the Journal Reports Citation and Metallurgical Engineering category, and reformulates queries when initial evidence is insufficient.
  arXiv  Detail & Related papers  (2026-05-10T13:00:32Z)
• Retrieval Augmented Generation of Literature-derived Polymer Knowledge: The Example of a Biodegradable Polymer Expert System [4.222675210976564]
  Polymer literature contains a large and growing body of experimental knowledge.<n>Much of it is buried in unstructured text and inconsistent terminology.<n>Existing tools typically extract narrow, study-specific facts in isolation.
  arXiv  Detail & Related papers  (2026-02-18T17:46:09Z)
• GRACE: Reinforcement Learning for Grounded Response and Abstention under Contextual Evidence [9.80421132842862]
  Retrieval-Augmented Generation (RAG) integrates external knowledge to enhance Large Language Models (LLMs)<n>RAG is susceptible to two critical flaws: providing correct answers without explicit grounded evidence and producing fabricated responses when the retrieved context is insufficient.<n>We propose GRACE, a reinforcement-learning framework that simultaneously mitigates both types of flaws.
  arXiv  Detail & Related papers  (2026-01-08T02:47:33Z)
• ReAG: Reasoning-Augmented Generation for Knowledge-based Visual Question Answering [54.72902502486611]
  ReAG is a Reasoning-Augmented Multimodal RAG approach that combines coarse- and fine-grained retrieval with a critic model that filters irrelevant passages.<n>ReAG significantly outperforms prior methods, improving answer accuracy and providing interpretable reasoning grounded in retrieved evidence.
  arXiv  Detail & Related papers  (2025-11-27T19:01:02Z)
• VeriCite: Towards Reliable Citations in Retrieval-Augmented Generation via Rigorous Verification [107.75781898355562]
  We introduce a novel framework, called VeriCite, designed to rigorously validate supporting evidence and enhance answer attribution.<n>We conduct experiments across five open-source LLMs and four datasets, demonstrating that VeriCite can significantly improve citation quality while maintaining the correctness of the answers.
  arXiv  Detail & Related papers  (2025-10-13T13:38:54Z)
• Causal-Counterfactual RAG: The Integration of Causal-Counterfactual Reasoning into RAG [2.3490649790592935]
  Large language models (LLMs) have transformed natural language processing (NLP), enabling diverse applications by integrating large-scale pre-trained knowledge.<n>Retrieval-Augmented Generation (RAG) addresses this challenge by combining retrieval mechanisms with generative modeling to improve contextual understanding.<n>We propose Causal-Counterfactual RAG, a novel framework that integrates explicit causal graphs representing cause-effect relationships into the retrieval process and incorporates counterfactual reasoning grounded on the causal structure.
  arXiv  Detail & Related papers  (2025-09-17T21:18:47Z)
• Prompting Large Language Models with Partial Knowledge for Answering Questions with Unseen Entities [43.88784275673178]
  Retrieval-Augmented Generation (RAG) shows impressive performance by supplementing and substituting parametric knowledge in Large Language Models (LLMs)<n>We show how triplets located in the gold reasoning path and their variants are used to construct partially relevant knowledge by removing the path that contains the answer.<n>Our awakening-based approach demonstrates greater efficacy in practical applications, outperforms traditional methods that rely on embedding-based similarity.
  arXiv  Detail & Related papers  (2025-08-02T09:54:46Z)
• Causal Discovery from Data Assisted by Large Language Models [50.193740129296245]
  It is essential to integrate experimental data with prior domain knowledge for knowledge driven discovery.<n>Here we demonstrate this approach by combining high-resolution scanning transmission electron microscopy (STEM) data with insights derived from large language models (LLMs)<n>By fine-tuning ChatGPT on domain-specific literature, we construct adjacency matrices for Directed Acyclic Graphs (DAGs) that map the causal relationships between structural, chemical, and polarization degrees of freedom in Sm-doped BiFeO3 (SmBFO)
  arXiv  Detail & Related papers  (2025-03-18T02:14:49Z)
• Harnessing Large Language Models for Knowledge Graph Question Answering via Adaptive Multi-Aspect Retrieval-Augmentation [81.18701211912779]
  We introduce an Adaptive Multi-Aspect Retrieval-augmented over KGs (Amar) framework.<n>This method retrieves knowledge including entities, relations, and subgraphs, and converts each piece of retrieved text into prompt embeddings.<n>Our method has achieved state-of-the-art performance on two common datasets.
  arXiv  Detail & Related papers  (2024-12-24T16:38:04Z)

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.