#evidence-retrieval News & Analysis

5 articles tagged with #evidence-retrieval. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

5 articles

AIBullisharXiv – CS AI · Jun 106/10

🧠

Divide and Cooperate: Role-Decomposed Multi-Agent LLM Training with Cross-Agent Learning Signals

Researchers propose DAC (Divide and Cooperate), a multi-agent training framework that separates evidence retrieval and answer generation into two specialized agents with cross-agent learning signals. This approach addresses credit assignment problems in language models performing multi-step reasoning and achieves competitive performance using parameter-efficient LoRA modules, outperforming full fine-tuning baselines on QA benchmarks.

AINeutralarXiv – CS AI · Jun 86/10

🧠

EASE-TTT: Evidence-Aligned Selective Test-Time Training for Long-Context Question Answering

Researchers present EASE-TTT, a novel framework combining within-context retrieval with test-time adaptation to improve long-context question answering in smaller language models. The method identifies evidence chunks and converts them into soft attention supervision targets, allowing models to focus on relevant information while processing the full context, outperforming existing retrieval-only and generic adaptation baselines.

AINeutralarXiv – CS AI · May 286/10

🧠

Checking Fact with Better Retrieval: Dynamic Contrastive Learning for Evidence Retrieval

Researchers propose DACLR, a dynamic contrastive learning method that improves evidence retrieval for multimodal fact-checking by converting diverse media types to text and extracting event-level features. The approach uses a two-stage recall-rerank system with adaptive loss functions to better match claims with relevant evidence rather than merely semantically similar content.

AINeutralarXiv – CS AI · Apr 156/10

🧠

TRUST Agents: A Collaborative Multi-Agent Framework for Fake News Detection, Explainable Verification, and Logic-Aware Claim Reasoning

TRUST Agents is a multi-agent AI framework designed to improve fake news detection and fact verification by combining claim extraction, evidence retrieval, verification, and explainable reasoning. Unlike binary classification approaches, the system generates transparent, human-inspectable reports with logic-aware reasoning for complex claims, though it shows that retrieval quality and uncertainty calibration remain significant challenges in automated fact verification.

AINeutralarXiv – CS AI · Mar 35/106

🧠

Multi-Sourced, Multi-Agent Evidence Retrieval for Fact-Checking

Researchers propose WKGFC, a new AI system that uses knowledge graphs and multi-agent retrieval to improve fact-checking accuracy. The system addresses limitations of current methods that rely on textual similarity by implementing an automated Markov Decision Process with LLM agents to retrieve and verify evidence from multiple sources.