Question Answering

Also known as QA

Follow this topic Ask about this topic

Momentum

23 papers in the last four weeks, up 28% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 165

All topics

Learning Evidence Sufficiency Boundaries for Selective Answering in Grounded Multi-Hop QA
Sep 1, 2026Haruto Sato, Yuki Tanaka, Ren Nakamura +2Multi-Hop QA Evidence-Grounded Reasoning
Independent Researcher
EDRAC: Benchmarking Arabic Dialect Reading Comprehension
Sep 1, 2026Noor Abo Mokh, Kirill Chirkunov, Teresa Lynn +15LLM Evaluation Arabic NLP
Mohamed bin Zayed University of Artificial Intelligence · New York University Abu Dhabi · IBM Research AI +1
Staged Linguistic Seeding: Grounded Query Expansion for Verified-Unit QA in AI Contact Centers
Sep 1, 2026Hyeonseop Yoon, Jeong-Eun ParkCustomer Support Automation Question Answering
Independent Researcher Seoul, South Korea
Dense Process Supervision for Search Agents via Fact Utility Estimation
Sep 1, 2026Rongzhi Zhu, Xiangyu Liu, Yi Liu +7Reinforcement Learning Credit Assignment in RL
State Key Laboratory for Novel Software Technology, Nanjing University, China · Ant Group, China · National Institute of Healthcare Data Science, Nanjing University, China
A Storage-Retrieval Gap in Parametric Knowledge Graph Memory
Aug 26, 2026Martino M. L. Pulici, Cuong Xuan Chu, Evgeny Kharlamov +1Knowledge Graph Question Answering Retrieval-Augmented Generation
Bosch Center for Artificial Intelligence, Robert-Bosch-Campus 1, 71272 Renningen, Germany · LMU Munich, Institute for Informatics, Oettingenstraße 67, 80538 Munich, Germany · University of Oslo, Department of Informatics, Gaustadalléen 23 B, 0373 Oslo, Norway +1
Credal Large Language Models for Semantic Commitment under Uncertainty
Aug 24, 2026Shireen Kudukkil Manchingal, Sofiia Nikolenko, Fabio CuzzolinSelective Prediction Confidence Estimation in Language Models
Oxford Dynamics Oxford · Ludwig-Maximilians-Universität München Munich · Institute for Artificial Intelligence, Data Analysis and Systems (AIDAS) School of Engineering Computing & Mathematics Oxford Brookes University, Oxford, UK
post-graph-rag: A PostgreSQL-Native Bi-Temporal Graph RAG Engine with Temporal Grounding at Synthesis
Aug 14, 2026Chandan RajahKG Construction LLM Reasoning with Graphs
Independent Researcher
Are You Sure You're Sure? On the Impact of Instruction Tuning on Confidence and Lexical Diversity
Aug 13, 2026Irina Proskurina, Mayank Kumar, Oyindolapo O. KomolafeConfidence Estimation in Language Models Question Answering
Cohere Labs Community · Laboratoire Hubert Curien, UMR CNRS 5516, Saint-Étienne, France · School of Computer Science Engineering and Technology (SCSET), Bennett University, Greater Noida, India +1
Better Decomposition, Free Aggregation: A Synthesizer-Folding Framework for Multilingual Multi-Hop Question Answering
Aug 13, 2026Yilin Wang, Yuchun Fan, Weidong Bao +5Multi-Hop QA Retrieval-Augmented Generation
School of Computer Science and Engineering, Northeastern University, Shenyang, China · Yunnan Key Laboratory of Artificial Intelligence, Kunming University of Science and Technology, Kunming, China
From Atomic Evidence to Logical Composition: Structured Compositional Reasoning over Compound Answer Options
Aug 13, 2026Obed Junias, Maria Leonor PachecoCompositional Reasoning Multiple-Choice Question Answering
University of Colorado Boulder
Asymptotic Risk Calibration for Selective Question Answering
Aug 12, 2026Shufan Lin, Sijin DongQuestion Answering LLM Uncertainty Estimation
Zhangjiang University · Ibaraki University
Assessing Reliability of BERT-Based Models on Question Answering Tasks
Aug 11, 2026Pooja Yadav, Priyanka Harjule, Basant Agarwal +1Question Answering Language Model Robustness
Department of Mathematics, Malaviya National Institute of Technology, Jaipur, Rajasthan, India · Department of Computer Science and Engineering, Central University of Rajasthan, Kishangarh, Rajasthan, India · University of Ljubljana, Faculty of Computer and Information Science, Ljubljana, Slovenia
Rethinking LLM Verification: Evidence Structure, Uncertainty, and Selective Refinement
Aug 11, 2026Uma Ranjan, Kunal Tilaganji, Aditya Koul +9LLM Grounding LLM Answer Verification
Indian Institute of Technology Jammu · Microsoft Research · SCB Dental College and Hospital, Cuttack
KGCaRe: Explainable Complex Conditional Question Answering using Automatic Knowledge Graph Construction and Context Retrieval with LLMs
Aug 10, 2026Ghanshyam Verma, Simanta Sarkar, Devishree Pillai +6KG Construction Graph Retrieval-Augmented Generation
Insight Research Ireland Centre for Data Analytics, Data Science Institute, University of Galway, IDA Business Park, Galway, H91 AEX4, Co. Galway, Ireland. · Fidelity Investments, Boston, Massachusetts, USA. · Fidelity Investments, Dublin, Co. Dublin, Ireland.
Forgotten History or Test-of-Time? Retrospect and Prospect on RAG from an IR Perspective
Aug 9, 2026Xiaoyan Zhao, Yujie Cai, Yang Zhang +2Retrieval-Augmented Generation Question Answering
National University of Singapore · Georgetown University
Don't `Well, Actually' Me Unless You Know What You're Talking About: Weak Presupposition Verification Degrades General QA Performance
Aug 6, 2026Shenran Wang, Vered Shwartz, Hila GonenLLM Evaluation LLM Answer Verification
Department of Computer Science, University of British Columbia · Vector Institute · CIFAR AI Chair +1
NeSy-RAG: Neuro-Symbolic RAG for Explainable Question Answering
Aug 6, 2026Jonas Gann, Michael GertzRetrieval-Augmented Generation Question Answering
Data Science Group, Heidelberg University, Germany
IslamicTurathBench: A Multi-Task, Multi-Discipline Benchmark for Evaluating Large Language Models on the Islamic Scholarly Tradition (turath)
Aug 5, 2026Shahd Gaben, Heba Sbahi, Samer Rashwani +5LLM Evaluation Benchmark Design
Hamad Bin Khalifa University, Doha, Qatar. · Nazarbayev University, Astana, Kazakhstan.
D $^2$ F-ReAG: Dynamic Decomposition and Filtering for Multi-Hop Reasoning-Augmented Generation
Aug 5, 2026Jiaoyang Li, Junhao Ruan, Shengwei Tang +4Multi-Hop QA Retrieval-Augmented Generation
Northeastern University, Shenyang, China · Kunming University of Science and Technology, Kunming, China · NiuTrans Research, Shenyang, China
Detecting Hallucinations and Recovering Verified Answers in Arabic Islamic Question Answering
Aug 4, 2026Khaled ZianiLLM Answer Verification Question Answering
Independent Researcher, Paris, France
VetScore: Risk-Weighted Fact Verification for Veterinary Long-Form QA with Citations
Aug 4, 2026Ivan Kartáč, Jan Tovarys, Mateusz Lango +1LLM Answer Verification Factual Consistency Evaluation
PrimVeterinary · Institute of Formal and Applied Linguistics, Charles University
Diversity is Not Ambiguity: Toward Accurate and Efficient Ambiguity Detection for Open-Domain QA
Aug 4, 2026Jiwon Lee, Yong-chan Park, Jungin Hong +1Question Answering Open-Domain QA
Seoul National University
Deep Agentic Search for Repository-Level Code Question Answering: An Empirical Study
Aug 2, 2026Amirkia Rafiei Oskooei, Bora Ilci, Alperen Kayim +5Agentic Search Semantic Search
Department of Computer Engineering, Yildiz Technical University, Istanbul, Turkey · Intellica Business Intelligence, Istanbul, Turkey
Verification Without Sufficiency: Per-Chunk Filtering Fails on Multi-Hop RAG, and Decomposition Repairs It
Aug 1, 2026Randhir KumarMulti-Hop QA LLM Answer Verification
Independent Researcher
AI and Authenticity in Islamic Research: A Critical Evaluation of Generative AI Reliability, Hallucination, and Source Fidelity in Quranic, Hadith, and Fiqh Knowledge
Jul 30, 2026Muhammad Sajjad AkbarQuestion Answering LLM Reliability
School of Computer Science, The University of Sydney, Australia
MMOOC: A Comprehensive Benchmark for Out-of-Context Evaluation in Multimodal Large Language Models
Jul 30, 2026Wenjie Zhu, Yabin Zhang, Wenjun Zeng +1VLM Robustness Multimodal Large Language Models
The Hong Kong Polytechnic University · Harbin Institute of Technology (Shenzhen) · Eastern Institute of Technology, Ningbo
ScalableRAG: High-Quality RAG at Zero Ingestion Cost
Jul 27, 2026Hilaf Hasson, Aditya Chakravarty, Jayant Thomas +1Retrieval-Augmented Generation Question Answering
1Cohesity
CAGE: Cognitive Attribution Graphs for Faithful Inline Citation Generation in Long-Form Question Answering
Jul 27, 2026Zhichao Yan, Shizhao Li, Jiapu Wang +5Retrieval-Augmented Generation Question Answering
Shanxi University, Taiyuan, China · Nanjing University of Science and Technology, Nanjing, China · Nanyang Technological University, Singapore +3
Data Quality over Capacity: Internalizing Documents into LoRA Adapters for Closed-Book QA
Jul 23, 2026Joan Figuerola HurtadoKnowledge Augmentation for Language Models LLM Fine-Tuning
Independent Researcher
When Trivia Is Not Trivial: Everyday Knowledge Failures in Multilingual LLMs
Jul 23, 2026Anna Mosolova, Djamé SeddahMultilingual Language Model Evaluation LLM Evaluation
INRIA Paris

Sep 1, 2026, cs.CLJ/K move · Enter open · S save

Learning Evidence Sufficiency Boundaries for Selective Answering in Grounded Multi-Hop QA

Haruto Sato, Yuki Tanaka, Ren Nakamura, Aoi Kobayashi+1

Independent Researcher

Multi-Hop QA Evidence-Grounded Reasoning Question Answering LLM Abstention

Open paper AskPDF arXiv

Grounded question answering systems should answer only when the supplied evidence supports the answer. In multi-hop QA, this requirement is difficult because partial evidence can make an unsupported answer appear plausible. We study selective answering through evidence sufficiency boundaries: for the same question, a model should abstain under unsupported or partially supported context, answer when the context first becomes sufficient, and keep the answer stable when redundant evidence is added. We introduce Evidence Sufficiency Boundary Training, a generation-native training framework that constructs ordered evidence chains and supervises the abstain-to-answer transition directly. The method combines level supervision, a boundary flip margin, post-boundary stability, and answer recall protection. We build evidence chains from HotpotQA, 2WikiMultiHopQA, and MuSiQue, then evaluate models with chain metrics, raw QA utility, and unsupported-answer rates on external non-answerable sets. With Qwen2.5-3B-Instruct and LoRA adaptation, Evidence Sufficiency Boundary Training gives the strongest boundary localization among the tested systems, with flip accuracy of 0.807 compared with 0.781 for a token-level abstention baseline. It also achieves the lowest overall unsupported-answer rate on external non-answerable evaluation, 0.095 compared with 0.101 for the same baseline, while retaining competitive raw QA F1. The results show that grounded selective answering improves when training marks the evidence level where refusal should give way to answering.

Momentum

Related topics

Latest papers 165