Papers with evidence grounding
R³A: Reinforced Reasoning for Relevance Assessment for RAG in User-Generated Content Platforms (2026.acl-industry)
Copied to clipboard
| Challenge: | Existing approaches to query–document relevance assessment are limited . ambiguous user intent and asymmetric relevance are challenges for RAG platforms . |
| Approach: | They propose a decomposed reasoning model for relevance assessment that decomposes query intent into intent inference and evidence grounding. |
| Outcome: | The proposed model outperforms strong baselines on offline benchmarks and achieves significant gains in large-scale online A/B testing. |
FinReporting: An Agentic Workflow for Localized Reporting of Cross-Jurisdiction Financial Disclosure (2026.acl-demo)
Copied to clipboard
Fan Zhang, Mingzi Song, Rania Elbadry, Yankai Chen, Shaobo Wang, Yixi Zhou, Xunwen Zheng, Yueru He, Yuyang Dai, Georgi Nenkov Georgiev, Ayesha Gull, Muhammad Usman Safder, Fan Wu, Liyuan Meng, Fengxian Ji, Junning Zhao, Xueqing Peng, Jimin Huang, YU Chen, Xue Liu, Preslav Nakov, Zhuohan Xie
| Challenge: | FinReporting is an agentic workflow for localized cross-jurisdiction financial reporting . existing approaches assume a single-market setting and overlook structural differences across jurisdictions . |
| Approach: | They propose a workflow that decomposes financial reporting into auditable stages . they use Large Language Models to extract and summarize corporate disclosures . |
| Outcome: | The proposed system decomposes reporting into auditable stages . it improves consistency and reliability under heterogeneous reporting regimes. |
The Confident Liar: Diagnosing Multi-Agent Debate with Log-Probabilities and LLM-as-Judge (2026.acl-srw)
Copied to clipboard
| Challenge: | Multi-agent debate systems are typically evaluated only on whether the final answer is correct, overlooking the quality of the intermediatereasoning that debate produces. |
| Approach: | They propose a framework that pairs a two-agent debate architecture with anLLM-as-judge that scores each agent’s reasoning along instructionfollowing, justification quality, and evidence grounding, together with acritical-failure flag. |
| Outcome: | The proposed framework pairs a two-agent debate architecture with anLLM-as-judge that scores each agent’s reasoning along instructionfollowing, justification quality, and evidence grounding, together with acritical-failure flag. |
PubMed Reasoner: Dynamic Reasoning-based Retrieval for Evidence-Grounded Biomedical Question Answering (2026.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to QA provide inaccurate answers but lack mechanisms to iteratively refine poor queries. |
| Approach: | They propose a biomedical question answering agent that performs self-critic query refinement . they propose re-reflection methods that kick in only after full retrieval is completed . |
| Outcome: | a biomedical question answering agent achieves 78.32% accuracy on PubMedQA . the proposed approach provides practical assistance to clinicians and biomedically researchers . |
Beyond Outcome Verification: Verifiable Process Reward Models for Structured Reasoning (2026.findings-acl)
Copied to clipboard
| Challenge: | Recent work on reinforcement learning with verifiable rewards (RLVR) has shown that large language models can be substantially improved using outcome-level verification signals. |
| Approach: | They propose a framework where intermediate reasoning steps are checked by deterministic, rule-based verifiers. |
| Outcome: | The proposed framework achieves 20% higher F1 than state-of-the-art models and 6.5% higher than verifiable outcome rewards, with substantial gains in evidence grounding and logical coherence. |
GAVEL: Evidence-Contract Debate with Mechanized Scrutiny for Provenance-Grounded Fact-Checking (2026.findings-acl)
Copied to clipboard
| Challenge: | Evidence-grounded fact-checking requires predicting claim veracity while returning faithful evidence at fine granularity. |
| Approach: | They propose a multi-agent debate framework that enforces evidence grounding throughout inference. |
| Outcome: | The proposed framework improves provenance-aware metrics over existing frameworks. |