BOUND refines LLMs' package-validity boundary via targeted editing to cut package hallucination rates by 79.9% on edit prompts and 65.4% on unseen prompts in recommendation tasks while generalizing to code generation.
Self-refine: Iter- ative refinement with self-feedback
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
years
2026 6representative citing papers
EvoVuln evolves executable detection policies for five smart-contract vulnerability types using cold-start synthetic testing followed by few-shot refinement on five vulnerable and five safe contracts, reaching 71% macro F1 and enabling a small model to beat a large zero-shot model by 19 points at un
AgentTether repairs 69% of initially failed LLM agent tasks on τ-bench by combining graph-guided root-cause diagnosis, cross-iteration repair memory, and guarded runtime intervention, improving over blind retry by 26 percentage points.
LLM-ReSum uses LLM self-evaluation in a closed feedback loop to refine summaries, improving factual accuracy by up to 33% and coverage by 39% with 89% human preference.
LongSumEval evaluates long-document summaries via answerability and factual alignment of generated QA pairs, yielding stronger human correlation than prior metrics and enabling iterative self-improvement.
Multi-agent AI agents answer questions alone then exchange reasoning to revise decisions, tested via experiments for net reliability gains versus error propagation.
citing papers explorer
-
Mitigating Package Hallucinations in Large Language Models via Model Editing
BOUND refines LLMs' package-validity boundary via targeted editing to cut package hallucination rates by 79.9% on edit prompts and 65.4% on unseen prompts in recommendation tasks while generalizing to code generation.
-
Knowledge Over Parameters: Evolving Smart Contract Vulnerability Detection
EvoVuln evolves executable detection policies for five smart-contract vulnerability types using cold-start synthetic testing followed by few-shot refinement on five vulnerable and five safe contracts, reaching 71% macro F1 and enabling a small model to beat a large zero-shot model by 19 points at un
-
AgentTether: Graph-Guided Diagnosis and Runtime Intervention for Reliable LLM Agent Operation
AgentTether repairs 69% of initially failed LLM agent tasks on τ-bench by combining graph-guided root-cause diagnosis, cross-iteration repair memory, and guarded runtime intervention, improving over blind retry by 26 percentage points.
-
LLM-ReSum: A Framework for LLM Reflective Summarization through Self-Evaluation
LLM-ReSum uses LLM self-evaluation in a closed feedback loop to refine summaries, improving factual accuracy by up to 33% and coverage by 39% with 89% human preference.
-
LongSumEval: Question-Answering Based Evaluation and Feedback-Driven Refinement for Long Document Summarization
LongSumEval evaluates long-document summaries via answerability and factual alignment of generated QA pairs, yielding stronger human correlation than prior metrics and enabling iterative self-improvement.
-
Preventing Error Propagation in Multi-Agent AI through Runtime Monitoring
Multi-agent AI agents answer questions alone then exchange reasoning to revise decisions, tested via experiments for net reliability gains versus error propagation.