Evidence-Grounded Reasoning

Follow this topic Ask about this topic

Latest papers 84

17 papers in the last four weeks, down 19% on the four weeks before. 0.1% of all new papers.

All topics

Cherry-pick Override: Unsafe Directional Commitment in LLM Judges under Mixed Evidence
Jun 5, 2026Haoran XuLLM-as-a-Judge Evidence-Grounded Reasoning
University of Glasgow
Quantum-Inspired Trace-Augmented Evidence Selection for Reasoning over Structured Hypothesis Spaces
Jun 5, 2026Laura Wynter, Nirvik Sahoo, Paul GriffinEvidence-Grounded Reasoning CoT Reasoning
School of Computing and Information Systems Singapore Management University Singapore
Evidence-Grounded Ensemble Diagnosis of 802.11 Packet Captures: A Multi-Stage Pipeline with Deterministic Reliability Scoring
Jun 5, 2026Jerome Henry, Swadhin Pradhan, Miroslav PopovicLLM Evaluation Evidence-Grounded Reasoning
Cisco Systems
Can Broad Biomedical Knowledge be Contextualized into Scenario-Grounded Propositions?
May 26, 2026Qingyuan Zeng, Ziyang Chen, Pengxiang Cai +5Evidence-Grounded Reasoning Scientific Hypothesis Generation
The Hong Kong University of Science and Technology (Guangzhou) · Guangzhou University of Chinese Medicine
PathoSage: Towards Multi-Source Evidence Adjudication in Pathology via Experience-Aware Agentic Workflow
May 18, 2026Chengyang Zhang, Wenchuan Zhang, Bo Li +5Computational Pathology Evidence-Grounded Reasoning
College of Computer Science, Sichuan University · Department of Pathology and Institute of Clinical Pathology, West China Hospital, Sichuan University · Department of Computer and Information Science, University of Macau +1
BELIEF: Structured Evidence Modeling and Uncertainty-Aware Fusion for Biomedical Question Answering
May 17, 2026Chang Zong, Hao Ning, Siliang Tang +2Healthcare Evidence-Grounded Reasoning
School of Computer Science and Technology, Zhejiang University of Science and Technology, Hangzhou 310023, China · College of Artificial Intelligence, Zhejiang University, Hangzhou 310027, China · Zhejiang Key Laboratory of Biomedical Intelligent Computing Technology, Zhejiang University of Science and Technology, Hangzhou 310023, China
Belief Engine: Configurable and Inspectable Stance Dynamics in Multi-Agent LLM Deliberation
May 14, 2026Joshua C. Yang, Maurice Flechtner, Damian Dailisan +1Belief Revision Evidence-Grounded Reasoning
ETH Zurich · ETH Zurich and Centre for Democracy Studies Aarau, University of Zurich · Massachusetts Institute of Technology
PlantMarkerBench: A Multi-Species Benchmark for Evidence-Grounded Plant Marker Reasoning
May 11, 2026Sajib Acharjee Dip, Song Li, Liqing ZhangLLM Evaluation Evidence-Grounded Reasoning
Department of Computer Science, Virginia Tech · School of Plant and Environmental Sciences, Virginia Tech · 3Health Sciences, Virginia Tech +2
Partial Evidence Bench: Benchmarking Authorization-Limited Evidence in Agentic Systems
May 6, 2026Krti TallamAgent Failure Analysis Evidence-Grounded Reasoning
KamiwazaAI
The Reasoning Trap: An Information-Theoretic Bound on Closed-System Multi-Step LLM Reasoning
May 3, 2026Kwan Soo ShinReasoning Evaluation Evidence-Grounded Reasoning
PolymathMinds AI Lab
FCMBench-Video: Benchmarking Document Video Intelligence
Apr 28, 2026Runze Cui, Fangxin Shang, Yehui Yang +3VLM Evaluation Document Understanding
AI Lab, Qifu Technology, Beijing, China · School of Future Technology, South China University of Technology, Guangzhou, China · Pazhou Lab, Guangzhou, China +1
GeoMind: An Agentic Workflow for Lithology Classification with Reasoned Tool Invocation
Apr 23, 2026Yitong Zhou, Mingyue Cheng, Jiahao Wang +2Evidence-Grounded Reasoning Agentic Workflows
State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China
Epistemic orientation in parliamentary discourse is associated with deliberative democracy
Apr 21, 2026Segun Aroyehun, Stephan Lewandowsky, David GarciaEvidence-Grounded Reasoning Political Discourse Analysis
Department of Politics and Public Administration, University of Konstanz, Germany. · School of Psychological Science, University of Bristol, UK. · Department of Psychology, University of Potsdam, Germany. +1
CulturALL: Benchmarking Multilingual and Multicultural Competence of LLMs on Grounded Tasks
Apr 21, 2026Peiqin Lin, Chenyang Lyu, Wenjiang Luo +22Multilingual Language Model Evaluation LLM Evaluation
Alibaba Group · Beijing Language and Culture University · LMU Munich +6
Case-Grounded Evidence Verification: A Framework for Constructing Evidence-Sensitive Supervision
Apr 10, 2026Soroosh Tayebi Arasteh, Mehdi Joodaki, Mahshad Lotfinia +2Evidence-Grounded Reasoning Reasoning Verification
RWTH Aachen University, Aachen, Germany
SemEval-2026 Task 12: Abductive Event Reasoning: Towards Real-World Event Causal Inference for Large Language Models
Mar 23, 2026Pengfei Cao, Mingxuan Yang, Yubo Chen +4Abductive Reasoning Causal Reasoning in Language Models
The Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China · School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China
TheraAgent: Multi-Agent Framework with Self-Evolving Memory and Evidence-Calibrated Reasoning for PET Theranostics
Mar 14, 2026Zhihao Chen, Jiahui Wang, Yizhou Chen +8Clinical Outcome Prediction LLM Agents
Fudan University · University of Bern · Nanjing University +1
Theoretical Foundations of Latent Posterior Factors: Formal Guarantees for Multi-Evidence Reasoning
Mar 13, 2026Aliyu Agboola AlegeEvidence-Grounded Reasoning
Epalea
Evidence-Driven Reasoning for Industrial Maintenance Using Heterogeneous Data
Mar 9, 2026Fearghal O'Donncha, Nianjun Zhou, Natalia Martinez +4Evidence-Grounded Reasoning AI-Assisted Decision Making
IBM Research Europe, Ireland · IBM Research Yorktown, USA · Imperial College London, UK
MIND: Unified Inquiry and Diagnosis RL with Criteria Grounded Clinical Supports for Psychiatric Consultation
Mar 4, 2026Guoyi Li, Shihao Xu, Jiatong Ma +4Healthcare Evidence-Grounded Reasoning
EverMind AI Inc., California, USA · Venus Team, Ant Group · Tianqiao and Chrissy Chen Institute, Shanghai, China +3
Evidence-Grounded Subspecialty Reasoning: Evaluating a Curated Clinical Intelligence Layer on the 2025 Endocrinology Board-Style Examination
Feb 17, 2026Amir Hosseinian, MohammadReza Zare Shahneh, Umer Mansoor +3Clinical Language Model Evaluation Evidence-Grounded Reasoning
January AI · Stanford University
To Retrieve or To Think? Cross-Boundary Context Evolution for Multi-hop Complex Reasoning
Jan 13, 2026Rubing Chen, Jian Wang, Wenjie Li +2Multi-Hop QA Retrieval-Augmented Generation
Department of Computing, The Hong Kong Polytechnic University
EpiQAL: Benchmarking Large Language Models in Epidemiological Question Answering and Reasoning
Jan 6, 2026Mingyang Wei, Dehai Min, Zewen Liu +8LLM Evaluation Healthcare
1Emory University · University of Illinois Chicago · 3Microsoft
Proof-of-Use: Mitigating Tool-Call Hacking in Deep Research Agents
Oct 13, 2025Shengjie Ma, Chenlong Deng, Jiaxin Mao +5LLM Agent Reliability RL for Tool Use
Gaoling School of Artificial Intelligence, Renmin University of China China · OPPO China

Jun 5, 2026J/K move · Enter open · S save

Cherry-pick Override: Unsafe Directional Commitment in LLM Judges under Mixed Evidence

Haoran Xu

University of Glasgow

LLM-as-a-Judge Evidence-Grounded Reasoning LLM Abstention Language Model Auditing

Open paper AskPDF arXiv

LLM judges increasingly turn verdicts into system commitments. Under mixed evidence (claims with both supporting and refuting sources) this is unsafe: when the schema exposes CONFLICTING as the authorized non-directional verdict, returning SUPPORTS/REFUTES is an unauthorized directional commitment, a failure we name Cherry-pick Override (CCO). We define CCO under an explicit task contract and report it with a same-denominator diagnostic protocol paired with matched-coverage bootstrap and an apples-to-apples random-veto null. On AVeriTeC's Conflicting subset (N_C = 150), three-option judges return a directional verdict on more than 84% of mixed-evidence claims; under the typed schema, three-judge majority voting amplifies direction-on-conflict on AVeriTeC (0.887 vs. 0.840; 95% CI [+0.013, +0.080]) but does not replicate on VitaminC-Mixed. Walking an intervention ladder of common single-channel fixes (typed vocabulary, panel aggregation, confidence thresholding, validator-only filtering), each leaves a distinct residual failure: panel aggregation suppresses single-judge CONFLICTING dissent in 48% of CCO cases; the panel is well-calibrated for direction (ECE = 0.07 on pure-S/R) so confidence cannot operationally separate CCO from correct directional commits; validator-as-classifier nearly halves pure-evidence accuracy. A minimal two-channel reference probe reaches operating points neither single channel reaches; under the random-veto null its promotion to CONFLICTING is structurally targeted on AVeriTeC (empirical p < 1/2001) and weaker but in the same direction on VitaminC-Mixed, a selectivity result rather than a magnitude one. We argue for an external commitment-control layer that separates verdict generation from commitment authorization, using structural evidence and confidence as orthogonal channels and NO-COMMIT as a routed controller state.