SEPs approximate semantic entropy from single-generation hidden states to enable cheap and robust hallucination detection in LLMs.
arXiv preprint arXiv:2305.15852 (2024) 37
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
DoLa reduces hallucinations in LLMs by contrasting logits from later versus earlier layers during decoding, improving truthfulness on TruthfulQA by 12-17 absolute points without fine-tuning or retrieval.
An A*-inspired multi-agent framework with hierarchical rewriting and a dynamic gamma parameter generates obfuscated prompts that achieve higher LLM attack success rates with fewer attempts than exhaustive search.
HalluClear supplies a taxonomy, calibrated evaluation, and lightweight post-training mitigation that reduces hallucinations in GUI agents using only 9K samples.
Sampling future contexts improves hallucination detection in black-box LLMs by exploiting the persistence of hallucinations.
HalluScan benchmark evaluates hallucination detection in LLMs, reporting NLI Verification at AUROC 0.88 and introducing HalluScore (r=0.41 with humans) plus Adaptive Detection Routing for 2x cost savings.
A survey that compiles and taxonomizes more than 32 existing hallucination mitigation techniques for LLMs while analyzing their challenges and limitations.
A survey classifying hallucination phenomena specific to large foundation models, establishing evaluation criteria, examining mitigation strategies, and discussing future directions.
citing papers explorer
-
Semantic Entropy Probes: Robust and Cheap Hallucination Detection in LLMs
SEPs approximate semantic entropy from single-generation hidden states to enable cheap and robust hallucination detection in LLMs.
-
DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models
DoLa reduces hallucinations in LLMs by contrasting logits from later versus earlier layers during decoding, improving truthfulness on TruthfulQA by 12-17 absolute points without fine-tuning or retrieval.
-
Dive into Ambiguity: A*-Inspired Multi-Agents Commonsense Obfuscation Attack on LLM Prompts
An A*-inspired multi-agent framework with hierarchical rewriting and a dynamic gamma parameter generates obfuscated prompts that achieve higher LLM attack success rates with fewer attempts than exhaustive search.
-
HalluClear: Diagnosing, Evaluating and Mitigating Hallucinations in GUI Agents
HalluClear supplies a taxonomy, calibrated evaluation, and lightweight post-training mitigation that reduces hallucinations in GUI agents using only 9K samples.
-
Enhancing Hallucination Detection via Future Context
Sampling future contexts improves hallucination detection in black-box LLMs by exploiting the persistence of hallucinations.
-
HalluScan: A Systematic Benchmark for Detecting and Mitigating Hallucinations in Instruction-Following LLMs
HalluScan benchmark evaluates hallucination detection in LLMs, reporting NLI Verification at AUROC 0.88 and introducing HalluScore (r=0.41 with humans) plus Adaptive Detection Routing for 2x cost savings.
-
A Comprehensive Survey of Hallucination Mitigation Techniques in Large Language Models
A survey that compiles and taxonomizes more than 32 existing hallucination mitigation techniques for LLMs while analyzing their challenges and limitations.
-
A Survey of Hallucination in Large Foundation Models
A survey classifying hallucination phenomena specific to large foundation models, establishing evaluation criteria, examining mitigation strategies, and discussing future directions.