LLM Grounding

LLM: Large Language Model

Follow this topic Ask about this topic

Momentum

25 papers in the last four weeks, up 127% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 216

Jul 2, 2026cs.AI

Verifiable Knowledge Expansion through Retrieval-Grounded Formal Concept Analysis

Ontology construction requires deciding which objects, attributes, and structural relations should be accepted as valid knowledge. Language models can propose such structures from text, but their outputs can still be unsupported or inconsistent. This paper proposes a retrieval-augmented small language model (SLM) framework that uses formal concept analysis (FCA) as a symbolic verification loop for knowledge expansion. Starting from seed attributes, FCA proposes implications over a growing formal context. A retrieval-grounded SLM oracle then validates each implication or returns a counterexample. The oracle also supports incidence judgments, consistency checks, and attribute proposals, making accepted implications, counterexamples, contradictions, and corrections inspectable. In a rare ataxia setting constructed from Orphadata resources, retrieval-grounded 10-seed runs obtain relation F1 of 0.29-0.52 and closure-based implication F1 of 0.22-0.30. Larger seed sets increase the number of evaluated implications and often improve implication F1. The lower implication scores reflect a stricter evaluation of derived implications, where one missed or extra relation can affect several implication judgments. Ablations show that incidence judgments in a fixed object-attribute setting can improve closure-based implication scores. However, identifying positive object-attribute pairs remains difficult even when the candidate objects and attributes are fixed.

Yujin Yang, Heejung Lee

Hanyang University Seoul, Korea

KG Construction LLM Grounding Knowledge Representation Formal Concept Analysis Ontology Learning

Jul 2, 2026cs.AI

EO-Agents: A Three-Agent LLM Pipeline for Earth Observation Hypothesis Generation

Large language models have recently been explored for scientific hypothesis generation, but most prior work relies on unstructured literature and free-form textual claims. We present a pipeline for Earth observation that grounds hypothesis generation directly in the NASA Earth Observation Knowledge Graph. A heterogeneous graph neural network trained on historical co-usage relations ranks candidate dataset pairings, and a three-agent LLM pipeline filters, generates, and evaluates structured research hypotheses. Applied to 1,475 NASA datasets, the system produces 160 hypotheses spanning multiple Earth-science domains, including ecohydrology, glaciology, aerosol--cloud interactions, vegetation phenology, and stratospheric chemistry. Model-predicted novel dataset pairings are rated nearly as plausible as held-out real co-usages from the literature, indicating that the pipeline surfaces scientifically coherent yet unexplored combinations. A 222 factorial experiment across GPT-5.2 and Claude Sonnet 4.6 shows that hypothesis rankings remain stable, while absolute scores depend strongly on judge identity, highlighting limitations of single-judge LLM evaluation.

Mahyar Ghazanfari, Amin Tabrizian, Armin Mehrabian +1

George Washington University, Washington, DC, USA · NASA Goddard Space Flight Center, Greenbelt, MD, USA · ADNET Systems, Inc., Bethesda, MD, USA

Multi-Agent LLM Systems LLM Grounding Scientific Hypothesis Generation Remote Sensing Research Idea Generation

Jul 1, 2026cs.CL

Grounded Optimization: A Layered Engineering Framework for Reducing LLM Hallucination in Automated Personal Document Rewriting

Large language models (LLMs) are increasingly applied to resume optimization for applicant tracking systems, introducing hallucination failures distinct from general text generation: anachronistic technology injection, cross-domain terminology contamination, structural mutation, and content fabrication. We present Grounded Optimization, a five-layer framework combining temporal context validation, deterministic contamination detection, structural invariant enforcement, prompt-level grounding, and an evaluator agent. In ablation experiments across three LLMs, four temperature settings, and six layer configurations on 25 synthetic resumes spanning 14 industries, undefended baselines produce 2.48-5.36 detected hallucinations per resume. Among detectors independent of the active defenses, temporal hallucinations are reduced by 50-95% across all conditions; overall detected hallucination rate falls to 0.04-0.24. Prompt-level grounding alone achieves zero detected hallucinations at low temperature with a capable instruction-following model; higher temperatures and weaker models reveal the need for the deterministic layers as a complement. We release the contamination taxonomy, evaluation code, and raw data.

Shashank Indukuri, Adarsh Agrawal

LLM Grounding LLM Hallucination Mitigation LLM Hallucination Detection

Jul 1, 2026cs.CL

RuleChef: Grounding LLM Task Knowledge in Human-Editable Rules

We present RuleChef, a framework that uses large language models (LLMs) to generate executable rules for NLP tasks such as text classification, Named Entity Recognition (NER), or relation extraction. Rules are generated based on a task description and a set of labeled examples, then they are iteratively improved based both on additional examples and on human feedback overexisting rules. RuleChef can also be used to bootstrap rules using the observed input-output pairs from any existing model for a given task. LLMs are used only at learning time, synthesizing rules and iteratively patching them based on failures measured on a held-out split. The result of this process is a fast, deterministic, and inspectable rule system. Preliminary evaluation is performed on both classification and NER tasks. We release RuleChef as open-source software under an Apache 2.0

Ádám Kovács, Nadia Verdha, Gábor Recski

KR Labs

LLM Grounding LLM-Based Program Synthesis Human-in-the-Loop AI

Jul 1, 2026cs.CL

Beyond Document Grounding: Span-Level Hallucination Detection over Code, Tool Output, and Documents

Hallucination detection for retrieval-augmented generation (RAG) is usually evaluated on natural-language document evidence. However, grounded generation systems increasingly rely on structured inputs: source code, developer-tool output, markdown documents, tables, and repository metadata. We introduce a unified benchmark for span-level hallucination detection over code, tool output, structured documents, and existing natural-language RAG datasets. The benchmark is built by starting from grounded correct answers, injecting localized hallucinations with exact character labels, and validating the code test split with evidence-based review. Our fine-tuned Qwen3.5-2B detector reaches 0.689 span-F1 on the unified test set and 0.60 on the code-agent source, where it substantially outperforms LettuceDetect-large (0.17) and the strongest zero-shot LLM judges we evaluated (at most 0.22). The same model remains competitive on established natural-language benchmarks, with 81.8 RAGTruth example-F1 and 0.724 English PsiloQA IoU.

Ádám Kovács, Bowei He, Xue Liu +3

KR Labs · MBZUAI · McGill University +1

LLM Grounding Hallucination Detection LLM Hallucination Detection RAG Robustness

Jul 1, 2026cs.CL

"Don't Say It!": Constraints, Compliance, and Communication when Language Models Play Taboo

The game of Taboo requires describing a target word without using a set of forbidden words, so that other players can guess it. This deceptively simple task combines strict lexical constraints with the need for communicatively effective descriptions, making it a compelling playground for examining how LLMs navigate competing demands at inference time. We evaluate two open-weight models under conditions that intervene at progressively deeper levels of the generative process, from prompting to generation-time constraints to internal representations manipulations. We assess their outputs through forbidden word violation detection, LLM-as-a-judge measuring the degree to which generated descriptions successfully evoke the target concept for both human and machine guessers, and examining whether the strategies models adopt under constraint align with those of human players. Our results show that compliance with the rules of the game and communicative effectiveness trade off differently across conditions, and that models remain substantially weaker than humans as guessers, suggesting that lexical grounding under constraint is an open challenge for current language models.

Sara Candussio, Francesca Padovani, Daniel Scalena +1

AILab, MIGe, Univeristy of Trieste, Italy · Center for Language and Cognition (CLCG), University of Groningen, The Netherlands · University of Milano - Bicocca, Italy

LLM Grounding Language Model Generation Evaluation Pragmatic Reasoning in Language Models Controllable Text Generation

Jun 30, 2026cs.CL

When LLMs Read Tables Carelessly: Measuring and Reducing Data Referencing Errors

While large language models (LLMs) perform well on table tasks, they still make data referencing errors (DREs), i.e., incorrectly citing or omitting table values, despite understanding the table structure. Beyond final-answer accuracy, DREs directly compromise the correctness and reliability of intermediate reasoning steps. Yet prior studies have only offered limited, small-scale analyses. In this work, we present the first systematic evaluation of tabular data referencing errors across different models and tasks. Our results show that DREs occur across all tested models (1.7B to 20B parameters). Furthermore, we demonstrate that incorporating data referencing as a critic significantly improves answer accuracy up to 12.0%, through critic-based filtering and rejection sampling. Finally, we trained a lightweight 4B-parameter critic model that achieves an average F1 score of 78.2% in detecting both in-distribution and out-of-distribution DREs, and effectively assists inference for larger models.

Yuqing Yang, Qi Zhu, Zhen Han +5

University of Southern California · AWS AI Labs

LLM Evaluation LLM Grounding LLM Reliability

Jun 29, 2026cs.CL

Grounding LLM Reasoning under Incomplete Graph Evidence

Knowledge graphs can guide large language models (LLMs) reasoning, but the graph seen by a system is usually a retrieved, linked, temporally scoped, and incomplete evidence state rather than a complete account of truth. We develop a theoretical perspective on grounding observable LLM trajectories under such incomplete graph evidence.The evidence state induces entity anchors, typed relation residuals, path energies, and support regions, while the language model supplies a prior over candidate trajectories. We show that, under open-world incompleteness, no hard rule based only on the observed state can both reject every false unsupported trajectory and retain every true-but-unobserved one.We then characterize soft grounding as a KL-regularized deformation of the LLM prior: finite slack preserves support for unsupported but non-contradicted trajectories, whereas hard conditioning appears as an infinite-penalty limit.The framework also yields stability bounds under evidence perturbations and clarifies the constraint regimes appropriate for GraphRAG, KGQA, graph agents, constrained decoding, and faithful generation. The claims are evidence-relative: KG compatibility is treated as declared support, not factual truth.

Jiaqi Li, Fanghui Song

Tianjin Normal University, College of Computer and Information Engineering, Tianjin, China · Harbin Institute of Technology, School of Mathematics, Harbin, China

LLM Grounding LLM Reasoning with Graphs Evidence-Grounded Reasoning

Jun 28, 2026cs.CL

Travel-Oriented Reasoning Large Language Model via Domain-Specific Knowledge Graphs

Large language models (LLMs) demonstrate broad reasoning abilities but struggle with accuracy and reliability in specialized domains such as travel, where reasoning depends on precise definitions, rules, and expert-defined conceptual frameworks, and where confident but unfounded outputs arise from a reasoning failure in which the model has not internalized the underlying domain graph rather than from missing domain knowledge alone. We propose a modular pipeline for building a travel-domain reasoning LLM grounded in an expert-designed knowledge graph (KG). Our pipeline integrates a travel KG that encodes domain entities and their relationships, a bottom-up construction procedure that walks the KG to produce multi-hop question answer (QA) pairs, a supervised fine-tuning stage that embeds the domain knowledge into a reasoning-capable LLM using the generated QA pairs as auditable reasoning traces, and a travel-domain benchmark dataset that measures the fine-tuned model's accuracy and calibration. We evaluate our approach using Qwen3-4B with LoRA adaptation. Our reasoning model achieves an

82.4\%

exact match on the benchmark. This performance significantly outperforms the pretrained Qwen3-4B baseline at

22.4\%

. A calibration analysis decomposes the residual

17.57\%

of errors into two distinct failure modes: an over-confident multi-label decoder that predicts both correct answers plus one spurious option on most dual-answer mistakes, and a smaller reasoning failure on single-answer questions where the supporting facts are present in the KG but the model fails to reconstruct the correct multi-hop path. This split confirms that explicit KG-grounded reasoning substantially improves the accuracy and uncertainty interpretation of LLMs in specialized domains, and isolates per-option calibration and trace-length-aware decoding as the next axes of improvement.

Vignesh Ram Nithin Kappagantula, Shayan Hassantabar, Samuel Simpson +1

Expedia Group Seattle, Washington, USA

LLM Grounding LLM Reasoning with Graphs Question Answering Structured Reasoning LLM Reliability Knowledge Graph Question Answering+1

Jun 28, 2026cs.LG

KrishokChat: A Citation-Grounded Dataset and Benchmark for Bengali Agricultural Advisory

We present KrishokChat, the first citation-grounded Bengali agricultural instruction-tuning dataset for crop advisory in low-resource settings. We establish a foundation of 290 hierarchical Knowledge Nodes, extracting disease symptoms, management practices, chemical dosages, and verbatim citations from 129 domain-filtered agricultural manuals. Every training instance inherits a verified citation header, guaranteeing 100% citation provenance. Using a Partitioned Seed Generation Matrix, these nodes are expanded into 139,200 supervised fine-tuning pairs, and augmented with 5,300 chemical safety and 1,000 adversarial safety instances, yielding 145,500 QA pairs across 18 crop categories. To evaluate real-world performance, we introduce the Farmer Benchmark, comprising 1,001 authentic farmer queries curated from field surveys and digital portals. Empirical evaluation on Gemma-4-E2B reveals that while fine-tuning on KrishokChat vastly improves structured formatting, standalone models still struggle with exact chemical dosage generalization. This highlights the dataset's true value as a verified knowledge base for retrieval-augmented generation (RAG) rather than mere parametric memorization. All data, code, and benchmarks are released under CC-BY-4.0.

Khan Raiyan Ibne Reza, Omar Ibne Shahid

North South University Dhaka, Bangladesh

LLM Grounding Question Answering Synthetic Data Generation for Language Models Knowledge-Intensive QA

Jun 27, 2026cs.CL

Latent Bridges for Multi-Table Question Answering

We introduce GRAB, a constructor-encoder-bridge pipeline for table question answering. Our method lifts relational data into an heterogeneous graph, encodes it via message passing, and transfers the signals to an LLM through a small set of query-conditioned latent tokens. This provides the LLM with a compact, task-relevant structural representation together with the flattened text. Crucially, the LLM remains strictly frozen to preserve its general reasoning capabilities; we train only the lightweight graph encoder and latent bridge (91M parameters), allowing the entire pipeline to be trained efficiently. Our pipeline significantly improves performance on relational Question Answering, with the largest gains in demanding multi-table settings, offering an efficient, principled way to connect relational deep learning with LLMs.

Simone Varriale, Tamara Cucumides, Floris Geerts +1

1EURECOM · University of Antwerp

Table QA LLM Grounding Relational Reasoning

Jun 25, 2026cs.AI

Odyssey: Constructing Verifiable Local Truth-Preserving Foundation Models

We introduce a categorical framework called ODYSSEY for constructing verifiable, local truth-preserving foundation models as compositions of foundries: building-block architectural components that specify a cover of local contexts, local representation families, restriction maps, gluing rules, obstruction policies, update obligations, and human-facing views. A foundry is an organized sheaf of knowledge that carries within it an argumentation component. Concrete foundries are built from generic foundries such as evidence/argument, operational decision, institutional/financial, market meaning, scientific challenge, research-program, assistant-build, and evaluation-harness foundries. Universal Foundry Learning (UFL) formalizes foundry construction as a composition of left and right Kan extensions, with left Kan extension rolling local artifacts into candidate foundries and right Kan extension enforcing the restriction, gluing, obstruction, and argumentation conditions required for promotion. Foundry SQL (FSQL) is a small typed query surface for slicing maintained foundry artifacts that uses TICKET (Topos Integration using Causal Kan Extension Transformers) certification for admitting external or pre-built models into durable ODYSSEY state. ODYSSEY is fully implemented and tested across a wide spectrum of concrete foundries, showing that the same categorical machinery supports domain construction, artifact replay, sheaf diagnostics, grounded Toulmin/local-LLM scrutiny, residual-obstruction ledgers, and optimized TICKET-compatible causal-claim extraction across heterogeneous sources. This paper is to be presented as a 2.5 hour tutorial at ICML 2026. The tutorial home page is at https://bit.ly/4ajS0nA.

Sridhar Mahadevan

Adobe Research · University of Massachusetts, Amherst

LLM Grounding Formal Verification Computational Argumentation LLM Honesty

Jun 25, 2026cs.AI

LCAi: Life Cycle Assessment with big data fusion and retrieval-augmented generation-assisted interpretation

The interpretation phase of life cycle assessment often lacks structured mechanisms for translating quantified improvement opportunities addressing environmental hotspots into actionable strategic pathways under technological, social, and policy uncertainty. To overcome this limitation, this study introduces a perspective-conditioned retrieval-augmented generation framework for LCA interpretation, where a multi-perspective retrieval and controlled synthesis is incorporated in the artificial intelligence (AI)-assisted LCA. To operationalise large language models in LCA interpretation, a perspective fusion RAG architecture was developed, covering academic, industry, public discourse, and European union (EU) funding datasets. Our approach comprises three steps: (1) a scenario anchor defining system boundaries and decarbonization targets, (2) a set of perspective-specific micro-queries with constrained retrieval, and (3) a neutral synthesis step integrating only ledger-stored outputs without further retrieval. The framework is demonstrated through a hydrogen-enabled diesel reduction use case in an Italian apple production facility using GPT-5 nano as the reasoning model. Overall, the structured retrieval and constrained synthesis are designed to mitigate the risk of hallucination while preserving cross-domain diversity. The approach presented can support more disciplined translation of impact results into strategic pathways and opens up new avenues for the use of advanced AI tools in LCA studies, particularly those focused on technologies that could be deployed at scale. This proof-of-concept demonstrates how AI-assisted, evidence-grounded interpretation can support implementation-oriented decision-making beyond conventional LCA studies.

Georgios Tsironis, Juan D. Medrano-Garcia, Gonzalo Guillen-Gosalbez

Institute for Chemical and Bioengineering, Department of Chemistry and Applied Biosciences, ETH Zürich, Vladimir Prelog Weg 1, Zürich 8093, Switzerland · NCCR Catalysis, Zurich 8093, Switzerland

Retrieval-Augmented Generation LLM Grounding

Jun 25, 2026cs.AI

KARLA: Knowledge-base Augmented Retrieval for Language Models

We propose a new method that allows an LLM to automatically pull in factual knowledge from a knowledge base during token generation. This means that (1)~factual knowledge in the LLM output can be updated without retraining the LLM, (2)~facts in the LLM output can be traced to the knowledge base for transparency and explainability, and (3)~smaller models can achieve the same factual accuracy as larger models. Our core idea is to train the model to produce special tokens that trigger a query to the knowledge base. Our experiments show that our method improves factual grounding in both short and long-form generation, and allows factual revisions to take effect through KB edits rather than parameter updates.

Francois Crespin, Fabian M. Suchanek, Nils Holzenberger

IP Paris, LTCI · Télécom Paris · Institut Polytechnique de Paris, France

Retrieval-Augmented Generation LLM Grounding Knowledge Augmentation for Language Models Factual Knowledge in Language Models

Jun 25, 2026cs.AI

What the LLM Should Not Say: Boundary-Aware Context Grounding for A Seven-Channel EEG Agent

Large language models (LLMs) can make scientific software easier to use. However, a general model does not automatically know which measurements a particular sensor can support, which algorithms are implemented in the current software, or which conclusions are justified by a computed result. These distinctions are especially important for low-channel electroencephalography (EEG), where sparse spatial coverage and variable signal quality make plausible but unsupported interpretations easy to produce. We present NeuraDock Agent, an open-source architecture that separates a deterministic local EEG engine from a hardware-aware language layer. The numerical engine parses recordings, performs quality control, executes reviewed spectral workflows, and writes machine-readable artifacts. The LLM receives only a compact, allowlisted summary and a versioned context pack. The context describes the seven-channel hardware, reviewed workflows, result fields, implementation boundaries, scientific limits, and reference cases. Raw EEG and dense per-sample arrays remain local We evaluate the system at three levels. First, 12 recordings produced identical structured results over ten numerical repetitions, and a complete Rest/Task run produced identical result, report, and figure hashes over three repetitions. Second, request-capture and failure-injection experiments confirmed the tested data boundary and preservation of local artifacts under HTTP, malformed-output, and connection failures. Third, a boundary-awareness benchmark tested 36 ordinary and adversarial questions under four context ablations and two LLMs, yielding 288 outputs.These results support hardware- and implementation-aware grounding as a practical mechanism for calibrating what an EEG agent accepts, qualifies, or refuses; they do not establish clinical validity or a validated absolute cognitive-load index.

Zhiyuan Xu, Yueqing Dai, Junling Li +1

Shanghai Pulse Element Intelligent Technology Co., Ltd. (NeuraDock)

Electroencephalography LLM Grounding LLM Agent Evaluation LLM Context Management LLM Agent Reliability

Jun 24, 2026cs.IR

How Large Language Models Source Brand Reputation Across Languages and Markets

When a large language model (LLM) answers a question about a company, it grounds the answer in retrieved web sources, and those sources decide what the model says. Most analysis of AI brand visibility looks at the answer text. This study looks one step earlier, at the citations. We merge three Rankfor.AI datasets covering 128 brands across 12 home markets and 13 languages, and analyse 167,551 URL-grounded citations (189,974 total attribution rows). We classify each citation by domain and source type and measure where AI gets its brand information, by language and by market. Four patterns hold. First, AI grounds brand answers overwhelmingly in third-party sources: 85.7% of citations point to sites the brand does not own, against 14.3% owned. Second, the source base is concentrated and long-tailed: 80% of citations come from about 18% of domains, fitting a Zipf law (alpha = 0.86, R^2 = 0.983). Third, one reference site dominates almost everywhere: Wikipedia is the most-cited domain in 11 of 12 languages, the exception being Lithuanian, where the business daily vz.lt edges it (4.38%). Fourth, the source mix is market-specific at the margin: for 46 Polish national brands the most-cited domain is YouTube, and four HR and careers portals supply 637 citations against 297 for Polish Wikipedia, about twice as many.

Dmitrij Zatuchin

Department of Information Technologies, Estonian Entrepreneurship University of Applied Sciences (EUAS), Tallinn, Estonia. · Rankfor.AI, Tallinn, Estonia.

Multilingual Language Models LLM Grounding

Jun 23, 2026cs.CL

Same Lesson, Different Story: Cross-Lingual Reconstruction of Cultural Narratives in Large Language Models

The evaluation of cultural grounding context becomes complex when multiple cultures convey the same moral lesson. This challenge is particularly relevant to large language models (LLMs), which produce narratives across a wide range of languages and cultural contexts. However, it remains uncertain whether these models preserve culturally grounded meaning when equivalent moral lessons are conveyed through distinct cultural forms. This study introduces a multilingual evaluation narrative framework that integrates a cross-linguistic collection of 414 proverbs spanning 15 languages and uses four LLMs to generate 13k narratives. By employing semantically equivalent proverbs as culturally grounded prompts, the analysis assesses whether models preserve meaning across languages, how cross-lingual conditioning influences narrative realization, and whether different model families converge on similar interpretations. Results indicate that cross-lingual prompting largely preserves proverb-level semantic meaning while systematically redistributing agency, social positioning, and narrative structure. Additionally, strong inter-model convergence is observed in both monolingual and cross-lingual settings, suggesting that multilingual LLMs rely on shared semantic abstractions despite architectural and linguistic differences. These findings shed light on the need for more comprehensive evaluations of cultural grounding. Relying exclusively on semantic similarity in multilingual narrative assessments may overestimate cultural preservation by neglecting culturally meaningful variations in narrative expression.

Jory Alshaalan, Haya Albaker, Abeer Aldayel +2

College of Computer and Information Sciences King Saud University, Saudi Arabia

Multilingual Language Model Evaluation LLM Grounding Text Generation Cross-Lingual Transfer

Jun 23, 2026cs.CL

AGORA: An Archive-Grounded Benchmark for Agentic Workplace Document Reasoning

Large language models are increasingly deployed as agents that reason over documents rather than answer from parametric knowledge. We study archive-grounded reasoning: locating sparse evidence across a large, messy collection of workplace files, reconciling inconsistent terminology, units, and time conventions, and computing an answer. Existing benchmarks address only parts of this setting and none jointly stresses archive-groundedness, agentic exploration, and cross-domain coverage. We introduce Agora, a benchmark pairing 362 questions with eight domain collections of 9,664 authentic documents and 372M tokens, far exceeding any model's context window, so agents must explore deliberately rather than scan exhaustively. Agora is built by an agentic pipeline combining cross-document task synthesis, leakage-preventing obfuscation, and difficulty filtering. Evaluating eight models, we find the task far from solved: even the strongest reaches only 59.4% accuracy, with notable variation across domains.

Honglin Guo, Qi Zhang, Yu Zhang +7

Fudan University · Zhejiang University · Shanghai Qiji Zhifeng Co., Ltd.

LLM Grounding Document QA Agentic Reasoning Agent Benchmarks

Jun 22, 2026cs.SE

DeepDiscovery: A Location-Inference Framework for Task-Level Repository Understanding

Large language models have shown strong performance on software engineering (SE) tasks, yet understanding large industrial repositories remains challenging. Existing methods often retrieve only local fragments and fail to recover the broader task-relevant context needed for complex repository-level tasks. We present DeepDiscovery, a task-level repository-understanding method for large industrial codebases. DeepDiscovery uses a two-stage \textit{Location--Inference} framework to localize high-confidence task anchors and recover broader task-relevant context over multi-relational repository structure under budget constraints. Across controlled method-level evaluation, organization-internal industrial repository-understanding scenarios, and end-to-end evaluation on SWE-bench Verified, DeepDiscovery consistently improves task-relevant file recovery and downstream SE performance. On 27 medium-scale tasks, DeepDiscovery achieves the best file recovery quality among five representative baselines without offline preprocessing. On organization-internal industrial tasks from a production-scale integrated codebase ecosystem, including 27 medium-scale tasks and 40 large-scale tasks, DeepDiscovery improves Full Recall Rate across multiple AI coding systems, with absolute gains ranging from 1.6 to 9.2 percentage points on large subprojects and from 2.5 to 7.4 percentage points on medium-scale subprojects. In a controlled end-to-end evaluation on SWE-bench Verified, a system equipped with DeepDiscovery achieves a 78.6% Solve Rate, outperforming the corresponding baseline by 8.2 percentage points. These results suggest that stronger task-level repository understanding can improve coding-agent performance on complex SE tasks.

Jiawei He, Weisong Sun, Mengyu Shi +4

AMAP, Alibaba Group · Nanyang Technological University · Nanjing University +1

LLM Grounding Software Engineering Agents

Jun 22, 2026cs.AI

GroundEval: A Deterministic Replacement for LLM-as-Judge in Stateful Agent Evaluation

Before letting an agent operate over real context, can you prove it used the right evidence? GroundEval turns that question into a deterministic test of what the agent searched, fetched, cited, and was permitted to access. In one case study, two frontier LLM judges scored a plausible agent response 0.85 and higher. But the trace told a different story: the agent had never retrieved the artifact its answer depended on, yielding a GroundEval score of 0.000. We introduce GroundEval, a judge-free framework for evaluating agents against grounded, time-bounded, and access-controlled evidence. GroundEval uses a domain configuration to generate questions, lets the agent choose how to answer, and then scores both the final answer and the recorded trajectory that produced it. The benchmark targets three failures that LLM-as-judge evaluation struggles to detect: whether an agent checked before claiming absence, reasoned only from evidence available to the actor at the relevant time, and used the correct causal mechanism rather than a plausible one. These correspond to three tracks: Silence, Perspective, and Counterfactual. GroundEval exposes when plausible answers rest on invalid evidence paths, and produces structured per-question diagnostics that pair tool activity with the agent's turn-level narration, making each score inspectable rather than merely reported. Our case studies suggest this failure mode is common rather than exceptional, one that final-answer and judge-based evaluation cannot detect by construction.

Jeffrey Flynt

Independent Researcher

AI Agent Reliability Tool-Use Evaluation LLM Grounding Tool-Augmented Language Model Agents LLM-as-a-Judge Language Model Generation Evaluation+4

Jun 21, 2026cs.CL

Knowledge-Graph Grounding Helps LLMs Only for Out-of-Training Knowledge: A Controlled Study on Clinical Question Answering

A recent Nature Medicine study reports that general-purpose frontier LLMs outperform specialized retrieval-augmented clinical tools on medical benchmarks, and that retrieval can hurt strong models. We ask the natural follow-up: does structured knowledge-graph (KG) grounding change this, and when does grounding help at all? We contribute two results. First, a reproduction: the study's headline HealthBench score (~88) is the Consensus variant, not full HealthBench, where frontier models and ideal completions both score ~46-47 under a physician-calibrated grader (agreement 82.5%); we reproduce GPT-5.2 Consensus =90.9 and flag a score-deflating grader bug. Second, a knowledge-boundary result. Using a graph+vector engine (samyama-graph) over the public biomedical KG PrimeKG, neither naive triple retrieval nor an agentic natural-language-to-Cypher loop (82% successful queries) improves MedQA across a weak-to-strong model ladder (all |Delta| <= 3.4). On a synthetic counterfactual KG, and on a hybrid benchmark mixing known and novel facts, the identical pipeline lifts out-of-training accuracy from chance to ~100% (+68 to +79) while adding nothing on known facts (a no-LLM arm answers both). Across three regimes (no-knowledge, graph-aided, hybrid), grounding helps only insofar as the decisive fact lies outside the model's training -- public-KG facts are redundant, private and novel data are where it pays -- matching the study's institutional-data caveat.

Madhulatha Mandarapu, Sandeep Kunkunuru

samyama

LLM Grounding LLM Reasoning with Graphs Clinical QA Factual Knowledge in Language Models Clinical Language Model Evaluation Biomedical KGs

Jun 19, 2026cs.CL

Beyond Hooking Onto the World: Referential Profiles and the Numerical Structure of LLM Grounding

This paper revisits the grounding problem for large language models in light of recent vector-grounding accounts. I accept the shift from classical symbol grounding to vector grounding, but argue that the current debate remains incomplete in two respects. First, reference is often treated too thinly, as if it were a fixed link between an isolated expression and an object. I argue instead that reference is profile-based, context-sensitive, discourse-level, affectively shaped, and norm-governed. Even in the human case, reference is publicly stabilized through patterns of use, correction, distinction, inference, and continuation rather than through identical private representations. Second, vector grounding requires an account of numerical realization. LLMs do not acquire reference through human perception, memory, intention, embodiment, or understanding. Rather, through optimization, they parameterize linguistic traces of human world-directed practice. In a finite vector system, referential profiles must be distributed, may be superposed, and are recovered through context-sensitive computation. Weights, activations, attention-mediated hidden states, softmax-trained contrasts, and inner-product alignments are the mathematical sites at which inherited linguistic relations become stable and causally active. Mechanistic interpretability findings, including entity-like features, knowledge neurons, and emotion-related activation directions, provide indirect support for this view. They do not show that LLMs possess human reference. They support a more limited thesis: LLMs may possess derivative, language-mediated, profile-based, and numerically structured forms of reference.

Joo Yull Rhee

Department of Physics, Sungkyunkwan University, Suwon, Republic of Korea.

Jun 19, 2026cs.CL

GRAG: Generic Response-Augmented Generation Framework for Personalized Conversational Systems

Deploying highly capable personalized conversational agents in resource-constrained or privacy-sensitive environments remains a significant challenge. We identify a fundamental bottleneck in the existing approaches: current training paradigms treat personalization and grounding as a single monolithic learning problem. Under these paradigms, language models are forced to simultaneously address what to say (content grounding) and how to say it in a user-specific way (personalization), which introduces significant computational and optimization challenges. Consequently, contextual grounding is often sacrificed for persona adherence, or vice versa, resulting in responses that are either weakly grounded in the conversational history or insufficiently personalized. In this work, we propose the Generic Response-Augmented Generation (GRAG) framework that decouples these competing objectives by leveraging offline, generic responses from high-capacity, general-purpose LLMs as a semantic and structural scaffold to guide the fine-tuning of smaller, task-specialized models seamlessly in resource-limited environments. By decoupling the content grounding from personalization, GRAG allows the model to focus exclusively on persona injection while remaining firmly anchored to the conversational context. We instantiate the GRAG in two post- and pre-fusion-based architectural variants and evaluate them on multiple benchmark conversational datasets that cover diverse personalization structures. Our results demonstrate that GRAG significantly outperforms state-of-the-art methods that do not use auxiliary scaffolding, yielding up to 47% improvements in ROUGE-2 and 36% in BLEU scores. Ultimately, GRAG offers a generalizable blueprint for building grounding-aware personalized conversational systems in resource-limited environments.

Junfeng Liu, Christopher T. Symons, Ranga Raju Vatsavai

North Carolina State University · Raleigh, NC, USA · Lirio, Inc. +1

LLM Grounding LLM Personalization Conversational Agents Persona-Conditioned Generation

Jun 18, 2026cs.IR

The Token Tax of Epistemic Accuracy: Comparing RAG and Long-Context Architectures for Document-Grounded Generative AI Applications

Document-grounded assistants built on large language models are increasingly used in high-stakes, knowledge-intensive work. Their usefulness, however, may depend on how evidence is allocated before generation. We investigate such a claim by comparing two grounding architectures: (a) retrieval-augmented generation (RAG) that retrieves a few relevant passages, and (b) long-context prompting, which loads the whole document collection in context. We view these as two regimes of "epistemic access" on an accuracy--cost frontier. We use "epistemic accuracy" to capture model correctness that depends on having the right evidence. We posit that broader access (via long context) can increase it, but with a "token tax" (i.e., a substantial increase in cost due to larger input token consumption). We probe this framing with a case study in manufacturing safety training. Using an expert-validated benchmark, we evaluate 972 answers across three machines, two small language models, and three retrieval/in-context prompting approaches. Long-context prompting achieved the highest correctness (73.1% vs. 65.4% for semantic RAG), but at 26 times the per-query token cost. We interpret this gap as the token tax of broader evidentiary access. We carefully discuss the implications of our findings for resource-constrained organizations.

Austin Hamilton, Ryan Singh, Michael Wise +6

Miami University · University at Buffalo

LLM Grounding LLM Inference LLM Prompting Document QA RAG Evaluation

Jun 17, 2026cs.AI

Decoupling Search from Reasoning: A Vendor-Agnostic Grounding Architecture for LLM Agents

Production LLM agents increasingly depend on real-time search, yet native search grounding bundles retrieval policy, provider choice, evidence injection, cost, latency, and generation behavior behind a single model-provider boundary. This coupling makes grounding hard to inspect, tune, reuse, or port, and can trigger Search-Induced Verbosity that breaks strict output contracts. We present Decoupled Search Grounding (DSG), a vendor-agnostic boundary that moves grounding outside the reasoning model through an MCP-compatible gateway, exposing provider routing, source-aware context rendering, configured fallback, retrieval-depth control, and exact plus semantic caching as first-class controls. Across five frontier models on SimpleQA, FreshQA, and HotpotQA, native search leads on recency-sensitive FreshQA, but DSG exposes a stronger frontier when control matters: on SimpleQA it nearly matches native accuracy (86.1% vs. 87.7%) at 91% lower search cost, preserves concise answer contracts, and reaches a 99.4% warm-cache hit rate with 68% lower latency. Deployed as a shared production grounding layer for large-scale agentic workloads with interchangeable models, DSG matches or slightly exceeds native-search accuracy on an e-commerce query-understanding (QIU) workload while cutting search cost by over 98%. Real-time grounding is best treated as an optimizable interface boundary, not a fixed model feature.

Emmanuel Aboah Boateng, Kyle MacDonald, Amardeep Kumar +2

DoorDash, Inc.

LLM Grounding Tool-Augmented Language Model Agents Agentic Search Agentic RAG

Jun 17, 2026cs.CL

The Wrong Kind of Right: Quantifying and Localizing Misfired Alignment in LLMs

Warning: This paper studies stereotypes and biases, and contains potentially disturbing examples, used for illustration purposes only. Our findings should not be interpreted as an argument against alignment. Instead, this paper highlights the need for principled approaches to more advanced alignment. Alignment aims to ensure that large language models (LLMs) behave safely and reliably, including by avoiding unsafe inferences. However, we show that such safety-oriented behaviors can misfire: models may reject warranted conclusions even when they are explicitly supported by context. We call this failure mode misfired alignment, where alignment-induced changes cause LLMs to override explicit evidence. To quantify this phenomenon, specifically on stereotype-related alignment, we introduce VETO, a benchmark consisting of 2,032 BBQ-derived contrastive pairs, and define a new metric, Misfired Alignment Rate (MAR), which measures on a 0 to 100 scale how often a model fails on a stereotype-related question but succeeds on its contrastive counterpart. We benchmark 25 LLMs on VETO, and show that all LLMs, including the most recent ones, exhibit non-trivial (4.7 to 18.9%) MARs while all human participants achieve 0.0% MAR. Controlled priming experiments further show that alignment-induced cues can substantially amplify MAR across LLMs, indicating that these failures are not merely artifacts of individual examples but can be induced by safety-related framing. Mechanistic analyses on open-weight LLMs reveal late-layer suppression of evidence-supported answers, and comparisons between instruct and base LLMs suggest that this suppression emerges after instruction training. These findings show that current alignment methods can overgeneralize surface-level safety cues, to the point of overriding objective evidence, motivating more work on alignment objectives that better preserve contextual grounding.

Naihao Deng, Yiming Feng, Chimaobi Okite +4

University of Michigan · University of Cambridge · University of Aberdeen

LLM Grounding LLM Alignment Language Model Safety Evaluation Social Bias in Language Models Language Model Bias Evaluation

Jun 16, 2026cs.AI

DiagFlowBench: Evaluating How Language Models Handle Off-Procedure Inputs in Grounded Diagnostic Dialogue

Language models increasingly serve as advisory systems in maintenance operations. To prevent hallucination, recent systems ground these models in procedural documentation to constrain them to approved steps. In practice, however, operator queries frequently stray from this path, requiring models to recognise out-of-scope inputs mid-conversation, a dynamic that current benchmarks rarely prioritise. We introduce DiagFlowBench, a dataset of 50 industrial diagnostic flowcharts from a consumer manufacturer converted into 1,676 multi-turn conversations that contrast compliant with out-of-scope utterances. Evaluating a panel of ten commercial and open-weight models reveals high variability in abstention rates, with models commonly selecting a real but contextually inadequate step rather than fabricating facts. The inherent plausibility and authority of this mapped but wrong advice exposes a challenging vulnerability for grounding systems.

Guillermo Gil de Avalle, Laura Maruster, Shaina Raza +1

University of Groningen, PO Box 72, 9700 AB Groningen, The Netherlands · Vector Institute for Artificial Intelligence, MaRS Centre, Toronto, ON, Canada

LLM Evaluation LLM Grounding LLM Abstention

Jun 15, 2026cs.AI

Consensus-based Agentic Large Language Model Framework for Harmonized Tariff Schedule Code Classification

Accurate Harmonized Tariff Schedule (HTS) code classification is essential for customs clearance, duty assessment, trade statistics, and regulatory compliance in maritime logistics. However, exact HTS classification remains challenging because product descriptions are often short, incomplete, or ambiguous, while correct classification depends on hierarchical tariff structures, legal notes, and jurisdiction-specific rules. This paper proposes an agentic large language model (LLM) framework for Canadian 10-digit HTS code classification in smart-port and maritime logistics environments. The framework integrates multi-agent information retrieval, semantic retrieval over official tariff documents, evidence-grounded reasoning, consensus-based validation, element-wise voting across hierarchical code components, confidence estimation, and human-in-the-loop escalation. We evaluate the framework on a private dataset of 3,300 domain-expert-labeled product records collected from logistics and delivery contexts. Experimental results show that exact 10-digit classification remains difficult even for advanced LLMs, with performance decreasing from coarse chapter-level prediction to fine-grained tariff and statistical suffix assignment. These findings demonstrate the need for evidence-grounded, uncertainty-aware, and human-centered classification workflows rather than fully autonomous single-step prediction. The proposed framework supports more interpretable, accountable, and compliance-oriented HTS classification for maritime logistics and smart-port operations. Our code is available at https://github.com/Analytics-Everywhere-Lab/hts.

Truong Thanh Hung Nguyen, Khanh Van Quynh Nguyen, Hoang-Loc Cao +5

Analytics Everywhere Lab, University of New Brunswick, Canada · University of Economics Ho Chi Minh City, Vietnam

Hierarchical Classification Multi-Agent LLM Systems LLM Grounding

Jun 15, 2026cs.CL

ACCORD: Action-Conditioned Contextual Grounding for Language Agents

User instructions are often underspecified because humans rely on implicit assumptions about the surrounding environment. For large language model (LLM) agents operating in information-rich digital and physical environments, these assumptions cannot be inferred from the instruction alone; they must be recovered from the current state of tools, data, interfaces, and observations. Effective execution therefore requires agents to identify missing context, ground it in observed evidence, and carry it forward into subsequent actions. We show that current agents often fail to do so. They act from assumed rather than observed specifics, overlook information they could have gathered, and fail to incorporate evidence that has already been returned. Building on this insight, we propose ACCORD (Action-Conditioned Contextual Grounding), a simple and effective agent framework for adaptive grounding. Before each action, ACCORD actively probes the environment for missing information and integrates relevant context from the agent's trajectory that would otherwise be overlooked. Requiring no additional training or task-success signals, ACCORD improves task-goal completion on AppWorld by up to +20.6 points with GPT-5-mini, from 42.0% to 62.6%, compared to strong baselines. These gains persist with a substantially stronger base model (+10.8 with Claude-4.5-sonnet), an open-weight model (+10.1 with Qwen3.5-27B-FP8), and on the embodied AlfWorld benchmark (+7.4 success rate with GPT-5-mini).

Lai Jiang, Cheng Qian, Zhenhailong Wang +3

University of Illinois Urbana-Champaign · Stanford University

LLM Grounding Tool-Augmented Language Model Agents Active Information Gathering LLM Agents LLM Context Management

Jun 15, 2026cs.CL

GRACE: Step-Level Benchmark for Faithful Reasoning over Context

Many reasoning tasks require models to reason over input context, from document-grounded question answering to rule-based deduction. Chain-of-Thought (CoT) prompting produces traces that appear transparent, yet individual steps can silently deviate from the source evidence, even when the final answer is correct. Existing methods detect hallucinations at the response level but fail to identify where in the chain a failure occurs or what type it is. We introduce GRACE, the first human-annotated step-level faithfulness benchmark with a data-driven error taxonomy for context-grounded textual reasoning. GRACE covers CoT traces from 10 models across 4 source datasets, with each step annotated for faithfulness, error category, and natural language explanation. A data-driven taxonomy, discovered bottom-up via unsupervised clustering, organizes failures into two tracks: GRACE-Inference (deductive errors) and GRACE-Grounding (factual grounding errors), with four categories each. The evaluation set is human-annotated and challenging by design. Our experiments reveal substantial headroom for current models. In addition, integrating step-level faithfulness signals into reinforcement learning pipelines improves both downstream accuracy and reasoning reliability.

Hoang Pham, Dong Le, Anh Tuan Luu

Nanyang Technological University · VinUniversity

CoT Faithfulness Contextual Faithfulness LLM Evaluation LLM Grounding Reasoning Trace Analysis