Pith. sign in

REVIEW 11 cited by

Chainpoll: A high efficacy method for LLM hallucination detection

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2310.18344 v1 pith:JJLPRENT submitted 2023-10-22 cs.CL cs.AIcs.LG

classification cs.CLcs.AIcs.LG
keywords chainpollhallucinationmetricsdetectionrealhalldatasetsllmsmethod
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Large language models (LLMs) have experienced notable advancements in generating coherent and contextually relevant responses. However, hallucinations - incorrect or unfounded claims - are still prevalent, prompting the creation of automated metrics to detect these in LLM outputs. Our contributions include: introducing ChainPoll, an innovative hallucination detection method that excels compared to its counterparts, and unveiling RealHall, a refined collection of benchmark datasets to assess hallucination detection metrics from recent studies. While creating RealHall, we assessed tasks and datasets from previous hallucination detection studies and observed that many are not suitable for the potent LLMs currently in use. Overcoming this, we opted for four datasets challenging for modern LLMs and pertinent to real-world scenarios. Using RealHall, we conducted a comprehensive comparison of ChainPoll with numerous hallucination metrics from recent studies. Our findings indicate that ChainPoll outperforms in all RealHall benchmarks, achieving an overall AUROC of 0.781. This surpasses the next best theoretical method by 11% and exceeds industry standards by over 23%. Additionally, ChainPoll is cost-effective and offers greater transparency than other metrics. We introduce two novel metrics to assess LLM hallucinations: Adherence and Correctness. Adherence is relevant to Retrieval Augmented Generation workflows, evaluating an LLM's analytical capabilities within given documents and contexts. In contrast, Correctness identifies logical and reasoning errors.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 11 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Decomposed Entailment for Factuality Checking and Hallucination Detection

    cs.CL 2026-08 conditional novelty 6.0 of 10

    HallDetect detects source-grounded hallucinations by decomposing responses into atomic claims and verifying each with a compact NLI model over multi-scale source chunks, outperforming frugal generative baselines on th...

  2. KEA Explain: Explanations of Hallucinations using Graph Kernel Analysis

    cs.LG 2025-07 conditional novelty 6.0 of 10

    A graph-kernel comparison of LLM-derived and ground-truth knowledge graphs detects hallucinations and produces contrastive explanations.

  3. Teaching Audio-Aware Large Language Models What Does Not Hear: Mitigating Hallucinations through Synthesized Negative Samples

    eess.AS 2025-05 conditional novelty 6.0 of 10

    A contrastive-style adapter trained on LLM-generated positive and negative audio descriptions improves audio hallucination accuracy to 77.5 percent and audio question answering to 84.3 percent, without changing the fr...

  4. Detection and Mitigation of Hallucination in Large Reasoning Models: A Mechanistic Perspective

    cs.AI 2025-05 reject novelty 6.0 of 10

    A logit-lens divergence score over late layers is used to detect hallucinated reasoning traces and to shape reinforcement learning rewards, with results on math, science, and multi-hop QA benchmarks.

  5. "Explain, Don't Just Warn!" -- A Real-Time Framework for Generating Phishing Warnings with Contextual Cues

    cs.CR 2025-05 conditional novelty 6.0 of 10

    PhishXplain uses a local LLM to generate real-time phishing warnings with annotated screenshots and contextual explanations, and a user study found these warnings improved later phishing detection.

  6. Harmonia: End-to-End RAG Serving Optimization

    cs.DC 2025-05 conditional novelty 6.0 of 10

    An end-to-end RAG serving framework that uses component-level batching, resource allocation, and runtime prioritization to improve throughput and reduce SLO violations.

  7. The HalluRAG Dataset: Detecting Closed-Domain Hallucinations in RAG Applications Using an LLM's Internal States

    cs.CL 2024-12 conditional novelty 6.0 of 10

    HalluRAG provides a recency-controlled dataset for closed-domain hallucination detection and shows that intermediate activation values carry hallucination signals as strongly as contextualized embeddings.

  8. ReXTrust: A Model for Fine-Grained Hallucination Detection in AI-Generated Radiology Reports

    cs.CL 2024-12 conditional novelty 6.0 of 10

    A self-attention model over hidden states of a vision-language model identifies hallucinated findings in AI-generated radiology reports with AUROC 0.8751, outperforming prior detectors.

  9. Not All Needles Are Found: How Fact Distribution and Don't Make It Up Prompts Shape Retrieval, Reasoning, and Hallucination in Long-Context LLMs

    cs.CL 2026-01 conditional novelty 5.0 of 10

    On a new extended needle-in-a-haystack benchmark, explicit anti-hallucination prompts and dispersed fact placement cause some long-context LLMs to over-refuse or collapse in accuracy, while others remain robust.

  10. Transparent NLP: Using RAG and LLM Alignment for Privacy Q&A

    cs.CL 2025-02 conditional novelty 5.0 of 10

    RAG systems with RAIN or MultiRAIN alignment outperform vanilla RAG on most privacy Q&A evaluation metrics, but none reach human expert quality and the approach is not yet practical.

  11. Challenges in Guardrailing Large Language Models for Science

    cs.AI 2024-11 conditional novelty 3.0 of 10

    A position paper proposing a guardrail framework with four dimensions (trustworthiness, ethics & bias, safety, legal) and implementation strategies for scientific LLM use.

Pith tools