Introduces unified span-level hallucination detection benchmark over code, tool output, and documents; fine-tuned Qwen3.5-2B reaches 0.689 span-F1 and outperforms baselines including on code-agent data.
Retrieval-augmented generation for knowledge-intensive NLP tasks , year =
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
roles
method 1polarities
use method 1representative citing papers
Quantile tokens inserted into LLM inputs combined with neighbor retrieval enable direct prediction of full distributions, yielding lower MAPE and narrower intervals than baselines on Airbnb and StackSample tasks.
ASB is a new benchmark that tests 10 prompt injection attacks, memory poisoning, a novel Plan-of-Thought backdoor attack, and 11 defenses on LLM agents across 13 models, finding attack success rates up to 84.3% and limited defense effectiveness.
Introduces predictive prefetching for RAG that anticipates retrieval needs several tokens ahead via three components, reporting up to 43.5% latency reduction and 62.4% TTFT improvement while preserving answer quality.
MixSD uses dynamic mixing of the model's expert and naive conditionals to create distribution-aligned supervision that improves the memorization-retention tradeoff over standard SFT.
ShinkaEvolve improves sample efficiency in LLM-driven program evolution via parent sampling, code novelty rejection-sampling, and bandit LLM ensemble selection, achieving new SOTA circle packing with 150 samples and gains on math reasoning and competitive programming tasks.
RGoT uses RL to adaptively generate task-specific graphs of operations for GoT-style LLM prompting from a human-provided set, with results suggesting feasibility under constraints.
KnowledgeBerg is a 4,800-question, 17-language benchmark showing LLMs fail at systematically enumerating bounded knowledge universes and performing compositional set-based reasoning over them.
Generative AI evaluation must shift from static benchmark scores to measuring sustained improvements in human capabilities within specific deployment contexts.
Position paper identifies three risks in the SEO-to-GEO transition and argues for answer-level governance focused on contestability, disclosure, auditing, and aligned metrics.
citing papers explorer
-
Beyond Document Grounding: Span-Level Hallucination Detection over Code, Tool Output, and Documents
Introduces unified span-level hallucination detection benchmark over code, tool output, and documents; fine-tuned Qwen3.5-2B reaches 0.689 span-F1 and outperforms baselines including on code-agent data.
-
Text-to-Distribution Prediction with Quantile Tokens and Neighbor Context
Quantile tokens inserted into LLM inputs combined with neighbor retrieval enable direct prediction of full distributions, yielding lower MAPE and narrower intervals than baselines on Airbnb and StackSample tasks.
-
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
ASB is a new benchmark that tests 10 prompt injection attacks, memory poisoning, a novel Plan-of-Thought backdoor attack, and 11 defenses on LLM agents across 13 models, finding attack success rates up to 84.3% and limited defense effectiveness.
-
Predictive Prefetching for Retrieval-Augmented Generation
Introduces predictive prefetching for RAG that anticipates retrieval needs several tokens ahead via three components, reporting up to 43.5% latency reduction and 62.4% TTFT improvement while preserving answer quality.
-
MixSD: Mixed Contextual Self-Distillation for Knowledge Injection
MixSD uses dynamic mixing of the model's expert and naive conditionals to create distribution-aligned supervision that improves the memorization-retention tradeoff over standard SFT.
-
ShinkaEvolve: Towards Open-Ended And Sample-Efficient Program Evolution
ShinkaEvolve improves sample efficiency in LLM-driven program evolution via parent sampling, code novelty rejection-sampling, and bandit LLM ensemble selection, achieving new SOTA circle packing with 150 samples and gains on math reasoning and competitive programming tasks.
-
Reinforced Graph of Thoughts: RL-Driven Adaptive Prompting for LLMs
RGoT uses RL to adaptively generate task-specific graphs of operations for GoT-style LLM prompting from a human-provided set, with results suggesting feasibility under constraints.
-
KnowledgeBerg: Evaluating Systematic Knowledge Coverage and Compositional Reasoning in Large Language Models
KnowledgeBerg is a 4,800-question, 17-language benchmark showing LLMs fail at systematically enumerating bounded knowledge universes and performing compositional set-based reasoning over them.
-
Benchmarked Yet Not Measured -- Generative AI Should be Evaluated Against Real-World Utility
Generative AI evaluation must shift from static benchmark scores to measuring sustained improvements in human capabilities within specific deployment contexts.
-
Position: Generative Engine Optimization Creates Underexamined Risks, Governance Must Target Concentration, Disclosure, and Academic Blind Spots
Position paper identifies three risks in the SEO-to-GEO transition and argues for answer-level governance focused on contestability, disclosure, auditing, and aligned metrics.