EnumGRPO is a self-improving optimizer for agentic query execution that reduces LLM-operator costs by ~317x while improving accuracy by 18% over a hybrid baseline across four databases.
Mixed citations
Mind the blind spots: A focus-level evaluation framework for LLM reviews
Mixed citation behavior. Most common role is background (40%).
15
Pith papers citing it
Background
40% of classified citations
citation-role summary
background 2
method 2
baseline 1
citation-polarity summary
representative citing papers
C-Mining automatically mines high-fidelity Culture Points from raw multilingual text by treating cross-lingual geometric isolation in embeddings as a quantifiable signal for cultural specificity, then uses them to synthesize better instruction data.
PRISM benchmark finds LLMs match or exceed humans on isolated review dimensions like novelty verification but none achieve the balanced performance of human reviewers across depth, flaw prioritization, and constructiveness.
GraphMind builds and evolves action-centric workflow graphs from traces, navigates them via multi-agent LLM reasoning, and adapts via ATR, outperforming baselines on 93 incidents with 8x less context and 26% lower hallucination in production deployment.
Empirical analysis of 4707 MoltBook posts shows AI-only technical discourse focuses on security, trust, and abstract topics while lacking concrete runtime and project details found in human GitHub discussions.
LLMs resist low-frequency permanent GPU faults but certain datapaths and precision formats trigger catastrophic training divergence even at moderate fault rates.
Entropy-gradient grounding uses model uncertainty to retrieve evidence regions in VLMs, improving performance on detail-critical and compositional tasks across multiple architectures.
RETINA-SAFE benchmark and ECRT two-stage triage improve hallucination risk detection in medical LLMs for retinal decisions by 0.15-0.19 balanced accuracy over baselines using internal representations and logit shifts.
Physician oversight reveals high error rates in LLM-generated labels for a clinical benchmark and demonstrates that corrected labels improve both evaluation accuracy and downstream model training.
LLMs exhibit 20-40% lower recall on ambiguous human names for PII detection, worsening under prompt injections, as shown via the new AmBench benchmark.
Constraining visual token budget per observation during VLM training forces genuine active perception and delivers 5% average relative improvement without auxiliary losses or architecture changes.
CroSearch-R1 applies search-augmented RL with cross-lingual integration and multilingual rollouts to improve RAG effectiveness on multilingual collections.
Human-written screenplays pass the Bechdel test more often than those generated by GPT-5, Gemini 3 Pro, and Claude Sonnet 4.5, though network analyses show mixed bias patterns across all script types.
LLM-based SE tools lack stable ground truth and deterministic outputs, making standard evaluation assumptions invalid and requiring new approaches for reliable assessment.
citing papers explorer
No citing papers match the current filters.