Skip to content
Preprint

Grounded Optimization: A Layered Engineering Framework for Reducing LLM Hallucination in Automated Personal Document Rewriting

Jul 2026 · 0 citations · 21 references
Computer Science

TL;DR

Grounded Optimization is presented, a five-layer framework combining temporal context validation, deterministic contamination detection, structural invariant enforcement, prompt-level grounding, and an evaluator agent for large language models for resume optimization.

Abstract

Large language models (LLMs) are increasingly applied to resume optimization for applicant tracking systems, introducing hallucination failures distinct from general text generation: anachronistic technology injection, cross-domain terminology contamination, structural mutation, and content fabrication. We present Grounded Optimization, a five-layer framework combining temporal context validation, deterministic contamination detection, structural invariant enforcement, prompt-level grounding, and an evaluator agent. In ablation experiments across three LLMs, four temperature settings, and six layer configurations on 25 synthetic resumes spanning 14 industries, undefended baselines produce 2.48-5.36 detected hallucinations per resume. Among detectors independent of the active defenses, temporal hallucinations are reduced by 50-95% across all conditions; overall detected hallucination rate falls to 0.04-0.24. Prompt-level grounding alone achieves zero detected hallucinations at low temperature with a capable instruction-following model; higher temperatures and weaker models reveal the need for the deterministic layers as a complement. We release the contamination taxonomy, evaluation code, and raw data.

View source

Similar papers

Review Open access Jul 2026

A Review of Hallucination Suppression Technologies for Large Language Models Under RAG Architecture

This review provides systematic theoretical support for industrial RAG model selection and optimization and summarizes existing research gaps, including lightweight deployment and multimodal expansion, and proposes future research directions for trustworthy RAG systems.

Shujing Liu · 0 citations
Preprint Jul 2026

Unified Hallucination Fuzzing for Multimodal Large Language Models

This work introduces UniHall, a fine-grained dataset grounded in a unified taxonomy spanning Object, Instruction, and Knowledge dimensions, and proposes Self-Adaptive Multimodal Fuzzing (SAMF), a self-adaptive framework that employs evolutionary mutation strategies to explore the boundaries of model hallucinations.

P. Zhou, Jiajun Song, Zhiwei Tang et al. · 1 citation
Preprint Aug 2026

Actionable Hallucination Detection: Translating Latent Uncertainty into Agentic Critique

The Latent Critic is introduced, a lightweight low-rank adapter that operates concurrently with a frozen base LLM's generation to actively restructure the transformer's residual stream---amplifying latent grounding signals and translating them into localized, natural language feedback within a single sequence.

S. Vijayvargiya, R. Lokesh · 0 citations
Book Open access Jul 2026

Understanding and Mitigating Hallucinations in Industrial LLM-based Unit Test Generation

Unit testing plays a critical role in ensuring software quality and reliability in large-scale industrial environments. While Large Language Models (LLMs) offer promising automated test generation capabilities, their practical deployment faces significant challenges due to hallucination problems. In this paper, we analyze compilation failures from LLM-generated unit tests in Ant Group's production systems and identify two fundamental types of hallucinations: extrinsic hallucinations caused by insufficient contextual information and intrinsic hallucinations stemming from model limitations even with adequate context. To address these issues, we propose DEHALL, an automated end-to-end unit test generation tool that systematically mitigates both types of hallucinations through comprehensive context construction and targeted static analysis-based repair. Our approach builds a heterogeneous graph to capture relevant context and employs specialized repair mechanisms for import, field, and method issues. Evaluation on Ant Group's internal datasets reveals that DEHALL achieves 71.56% line coverage and 67.18% branch coverage, significantly outperforming vanilla LLM approaches. In the public benchmarks, it also shows better performance on coverage and better defect detection capability than previous state-of-the-art approaches. DEHALL has been successfully deployed across multiple business domains at Ant Group, achieving an 81% developer adoption rate with positive user feedback on productivity improvements.

Yanlun Tu, Ziyue Zhou, Chengdong Xu et al. · 0 citations
Preprint Aug 2026

Decomposed Entailment for Factuality Checking and Hallucination Detection

HallDetect, a lightweight, reference-free, and black-box framework for hallucination detection, is presented, a lightweight, reference-free, and black-box framework for hallucination detection that is evaluated not only on summarization but across a broader range of source-grounded generation settings.

Achir Oukelmoun, N. Semmar, Gäel de Chalendar · 0 citations