LLM Answer Verification

LLM: Large Language Model

The field studies how to check an LLM’s answers, reasoning steps, citations, and evidence before accepting, revising, or abstaining from them. Approaches include retrieval and natural-language inference for evidence checking, symbolic tools and proof assistants for formal tasks, learned reward models for ranking candidate answers, and self- or cross-model review. These methods are tested in settings such as mathematical reasoning, multi-hop question answering, long-document and medical QA, and code or SQL generation, using benchmarks including MATH, GPQA, HotpotQA, FEVER, and BIRD. A central challenge is that verifiers can share a generator’s blind spots or reject valid answers, so accuracy must be balanced against calibration, evidence coverage, cost, and the risk of harmful revisions.

Latest papers

151 papers11 papers in the last four weeks, down 63% on the four weeks before. 0.1% of all new papers.

What Does an Ontology Catch? Curated, LLM-Generated and Data-Derived Ontologies as Checkers of LLM Agents over Knowledge Graphs
Oct 27, 2026Michal Orzechowski, Rund Tawfiq, Tomasz KosciolekLLM Answer Verification LLM Agent Evaluation
ACK Cyfronet AGH, Krakow, Poland · AGH University of Krakow, Krakow, Poland · Sano Centre for Computational Medicine, Krakow, Poland
Ask Before You Answer: A Question-Driven Evidence Reasoning Architecture (QERA) for In-Context Learning
Oct 26, 2026Jinhu Qi, Minda Hu, Wentao Zhang +2Evidence-Grounded QA Implicit Reasoning in Language Models
The Chinese University of Hong Kong Hong Kong, China · Macao Polytechnic University Macao, China · The Hong Kong Polytechnic University Hong Kong, China
Models Verify Sufficiency, Not Validity: Usable Falsehoods Evade the Checks that Gaps Trigger
Oct 25, 2026Naveen MadirajuLLM Reliability Language Model Reasoning Evaluation
Google, San Jose, CA, USA
Trust Mechanisms for Offline Generative AI at the Edge: A Connectivity-Regime Framework and an Empirical Study on a Raspberry Pi 5
Oct 24, 2026Georgios Feretzakis, Alexandros PapaspyridisLLM Reliability RAG Security
Recognizing Study Lineage Is Not Enough: Over-Crediting Same-Trial Evidence in LLM-Based Medical Verification
Oct 16, 2026Mukand Krishna, Anoushka Harit, Chenghao Xiao +1LLM Reliability LLM Answer Verification
School of Computing, University of Kent, UK · Cancer Research UK Cambridge Institute, University of Cambridge, UK · Shanghai University of Finance and Economics, China
Verification Turns Capability Gaps into Routing Decisions: Small Language Models for Clinical Documentation
Oct 13, 2026Nina Fatehi, Meysam Ghaffari, Animesh Agarwal +2Medical Report Generation Medical LLMs
Optum
Review Rarely Beats the Stronger Model: Separating Verification from Capability Transfer in LLM Pipelines
Oct 11, 2026Yirui Zhang, Yash Raj ShresthaLLM Answer Verification LLM Evaluation
University of Lausanne
VIGIL: Verifier-Informed Gated Improvement Loop for Spreadsheet Question Answering
Oct 3, 2026Kang Li, Lu He, Sandarsita GuntupalliTable QA Continual Learning for LLM Agents
Atlassian · Carnegie Mellon University
JOVE: Joint Execution and Verification for Resource-Aware LLM Task Graphs
Oct 2, 2026Haoran Zhang, Dongjun Kim, Seohyeon Cha +4LLM Inference Scheduling LLM Routing
University of Texas at Austin · DEVCOM Army Research Laboratory
What Was Said, Not What Was 'Thought': Type-6 Logic for CoT Verification
Sep 29, 2026Adrian de WynterLLM Answer Verification Dynamic Epistemic Logic
Microsoft and the University of York
Halluscoring 2026: The first shared task on llms hallucination detection and answer verification
Sep 29, 2026Aisha Alansari, Abdessalam Bouchekif, Ahmed Hasanaath +9LLM Evaluation LLM Answer Verification
King Fahd University of Petroleum and Minerals, Saudi Arabia · Hamad Bin Khalifa University, Qatar · University of the Basque Country, Spain +5
Locating Answer-Correctness Signals in Frozen Large Language Models
Sep 29, 2026Yuansen Liu, Yixuan Tang, Anthony Kum Hoe TungLLM Answer Verification Language Model Error Detection
School of Computing, National University of Singapore
Test-Time Scaling via Budgeted Multi-Attribute Verification
Sep 28, 2026Bo Xue, Ji Cheng, Shen-Huan Lyu +2Multi-Armed Bandits LLM Answer Verification
City University of Hong Kong · Hohai University · Zhejiang University
Risk-Controlled Selective LLM Answering by Pricing Label-Free Checks
Sep 27, 2026Dongyub Jude Lee, Jungseob Lee, Chanjun Park +2LLM Answer Verification Selective Prediction
Zoom Communications · Korea University · Soongsil University +1
Knowing Is Not Choosing: What Explicit Verification Adds Beyond Generative Preference
Sep 27, 2026Yilong Li, Chengpo Yan, Aayan Arish +1LLM Evaluation LLM Answer Verification
Department of Computer Science University of Wisconsin-Madison Madison, WI 53703, USA
BudgetVerify: Budget-Tiered Verification for Financial QA
Sep 27, 2026Janet Jenq, Hongda ShenLLM Answer Verification Reasoning Verification
PitchBook
Can You Check That? The Checkability Boundary for Local LLM Network Automation
Sep 25, 2026Maleeha Masood, Momina NofalLLM Answer Verification LLM Routing
University of Illinois Urbana-Champaign Urbana, IL, USA · Independent Researcher USA
Where Does Retrieval-Based Open-Ended Evaluation Fail? Automatic Taxonomy Induction from Long-Form Medical Answer Factuality Verification
Sep 24, 2026Heyuan Huang, Jirui Dai, Alexandra DeLucia +5LLM Answer Verification RAG Evaluation
Center for Language and Speech Processing Johns Hopkins University Baltimore, MD 21218, USA
Return or Revise? Learning When Revision Helps Retrieval-Augmented QA
Sep 24, 2026Nicholas Kashani Motlagh, Tim Anderson, Jeremy Gwinnup +1Retrieval-Augmented Generation LLM Answer Verification
DCS Corp · Air Force Research Laboratory
Cross-Lingual Legal QA for Vietnamese Labour Law: Retrieval, Translation, and Verifier-Guided Correction
Sep 23, 2026Nguyen Minh Chi, Mo El-Haj, Nguyen Ha Thanh +2LLM Answer Verification Legal Citation Verification
VinUniversity, Vietnam · Lancaster University, UK · Cardiff University, UK
Human-LLM Deliberation as Interactive Proof: Conditions for Verifiability Without Transparency
Sep 21, 2026Baotong Zhang, Dean Foster, João SedocLLM Answer Verification Anytime-Valid Inference
Stern School of Business, New York University, New York, NY, USA · Amazon, New York, NY, USA
From Tables to Quantified Statements: Evaluating LLM Inference Generation through Executable Verification
Sep 21, 2026Mai Mohamed Eida, Gunjan Anand, Ayush Singh +1Table QA LLM Evaluation
University of Illinois Urbana Champaign
EvidenT: Building Trustworthy Enterprise Assistants through Evidence Groundedness and Traceability
Sep 18, 2026Anubha Kabra, Katie Jooyoung Kim, Colin Zhiwei Kou +5Evidence-Grounded Generation Evidence-Grounded QA
Bloomberg
LLM-as-an-Improver: Turning Verification into Better Candidates
Sep 17, 2026Akiyoshi Tomihari, Yuma IchikawaLLM Answer Verification LLM Reranking
Fujitsu Limited Department of Computer Science The University of Tokyo · Fujitsu Limited RIKEN center for AIP
EviGen: Predictive Evidence Scaffolding for Verifiable Clinical Rationale Generation
Sep 16, 2026Fengnan Li, Heman Burre, Liwen Sun +2LLM Answer Verification Clinical Outcome Prediction
Duke University
Verifiable by Construction: Claim-Level Evaluation of Verbatim Citation in Clinical Question Answering
Sep 14, 2026Jiashuo Zhang, Yuling Chen, Yvonne Commodore-Mensah +1LLM Grounding LLM Answer Verification
Department of Computer Science Johns Hopkins University · School of Nursing Johns Hopkins University
MedSNIP: Building and Benchmarking Snippet-Level Granularity for Medical Fact Verification
Sep 11, 2026Hasan Iqbal, Sarfraz Ahmad, Hyunjae Kim +5LLM Answer Verification Automated Fact-Checking
Mohamed bin Zayed University of Artificial Intelligence · Yale University · Korea University +2
Can LLMs in Draft-Verify-Revise Pipelines Resolve Deictic Ambiguity?
Sep 10, 2026Obinna I. EkekezieCoreference Resolution LLM Answer Verification
Cambridge Health Alliance, Cambridge, MA, United States of America. · Harvard Medical School, Boston, MA, United States of America.
A decision-basis contract for auditable LLM-assisted medical billing verification: deterministic rules, verbatim evidence, and fail-closed abstention
Sep 10, 2026Jan Hölter, Kevin Geis, Benjamin Raab +1LLM Answer Verification LLM Auditing
Competence Center Artificial Intelligence, Aschaffenburg University of Applied Sciences, Würzburger Straße 45, Aschaffenburg, 63743, Bavaria, Germany.
NovGauge: A Fine-Grained Benchmark for Diagnosing LLMs' Capability in Paper Novelty Assessment
Sep 10, 2026Guoqiang Zhang, Kexin Tan, Ming Zhang +12LLM Evaluation LLM Answer Verification
College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China · Graduate School of Engineering, The University of Tokyo, Tokyo, Japan · AtomInnoLab +1

Oct 27, 2026J/K move · Enter open · S save

What Does an Ontology Catch? Curated, LLM-Generated and Data-Derived Ontologies as Checkers of LLM Agents over Knowledge Graphs

Michal Orzechowski, Rund Tawfiq, Tomasz Kosciolek

ACK Cyfronet AGH, Krakow, Poland · AGH University of Krakow, Krakow, Poland · Sano Centre for Computational Medicine, Krakow, Poland

LLM Answer Verification LLM Agent Evaluation Knowledge Graphs Knowledge Graph Question Answering

Open paper AskPDF arXiv

LLM agents that answer questions over Web knowledge graphs are increasingly wrapped in checks derived from the graph's ontology, on the assumption that a formal schema makes a reliable judge. Yet a checker can be wrong as well: it can miss errors, and it can flag correct answers and push the agent into "fixing" them. Whether a curated ontology is worth its cost as such a judge, and how it compares with an ontology an LLM writes or a schema mined from the data, is unknown. We make the checker itself the object of study. Across curated, LLM-generated and data-derived ontologies, used as prompt context, as a checker, or both, and across open-weight and proprietary agents on public graphs and a private graph of nearly

10^{9}

triples, we account for what ontology-derived checks catch and what they wrongly flag. We show how each source trades caught errors against false alarms, how a curated schema used as published can contradict its own data, which errors structural checks miss, and whether combining sources or giving the agent the checker's specific feedback pays off. On UniProt, the curated ontology flags more correct answers than either an ontology derived from the data or one an LLM derives from a summary of the data with masked identifiers. On real agent answers, its flags are only marginally more precise than random flags.