REVIEW 22 cited by
HaluEval: A Large-Scale Hallucination Evaluation Benchmark for Large Language Models
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
abstract
Large language models (LLMs), such as ChatGPT, are prone to generate hallucinations, i.e., content that conflicts with the source or cannot be verified by the factual knowledge. To understand what types of content and to which extent LLMs are apt to hallucinate, we introduce the Hallucination Evaluation benchmark for Large Language Models (HaluEval), a large collection of generated and human-annotated hallucinated samples for evaluating the performance of LLMs in recognizing hallucination. To generate these samples, we propose a ChatGPT-based two-step framework, i.e., sampling-then-filtering. Besides, we also hire some human labelers to annotate the hallucinations in ChatGPT responses. The empirical results suggest that ChatGPT is likely to generate hallucinated content in specific topics by fabricating unverifiable information (i.e., about $19.5\%$ responses). Moreover, existing LLMs face great challenges in recognizing the hallucinations in texts. However, our experiments also prove that providing external knowledge or adding reasoning steps can help LLMs recognize hallucinations. Our benchmark can be accessed at https://github.com/RUCAIBox/HaluEval.
Forward citations
Cited by 22 Pith papers
-
HumanAgencyBench: Scalable Evaluation of Human Agency Support in AI Assistants
A new benchmark finds low to moderate human agency support in 20 LLM assistants across six dimensions.
-
The Test Oracle Problem in Synthetic LLM-as-Judge Corpora: Disappearance, Distortion and a Validation Protocol
A silent truncation fault in an LLM-generated-negative corpus fabricated a robust bias effect; the paper shows this fault class is mechanically detectable only in perturbation-based corpora.
-
Confidently Wrong: Detecting Hallucinations in Financial Question Answering from LLM Internal States
Among 8/8 self-consistent answers on FinQA, residual-stream probes detect wrong answers at 0.68–0.77 AUROC versus 0.55–0.63 for the best cheap output baselines across three 8–9B models.
-
Reliability Scales Inversely: Hallucinations Snowball Faster in Bigger Language Models
Hallucination in LLMs is driven by an oracle-invisible “decoding risk” term that grows with scale and causally compounds errors within a response.
-
Decoding Memories: An Efficient Pipeline for Self-Consistency Hallucination Detection
A decoding pipeline reuses cached tokens and anneals sampling temperature to accelerate self-consistency hallucination detection by up to 3x without meaningful AUROC loss.
-
FECT: Factuality Evaluation of Interpretive AI-Generated Claims in Contact Center Conversation Transcripts
A new benchmark and 3D decomposition paradigm for factuality evaluation of interpretive claims about contact center conversations, with best LLM-judge F1 of 0.86.
-
Beyond Facts: Evaluating Intent Hallucination in Large Language Models
The paper proposes a query-centric evaluation of LLM "intent hallucination" via constraint decomposition, but the headline metric comparison is undermined by a self-referential human evaluation design.
-
HACo-Det: A Study Towards Fine-Grained Machine-Generated Text Detection under Human-AI Coauthoring
Current machine-generated text detectors, especially metric-based ones, perform poorly on word-level detection in coauthored texts, while finetuned DeBERTa achieves strong but imperfect performance.
-
Do You Keep an Eye on What I Ask? Mitigating Multimodal Hallucination via Attention-Guided Ensemble Decoding
Ensemble Decoding reduces object hallucination in large vision-language models by ensembling logits from attention-weighted image sub-images.
-
X$^3$-OPD: Distilling Reasoning into Large Audio-Language Models via On-Policy Alignment
X3-OPD improves audio-grounded reasoning by training the audio student on its own rollouts with token-level teacher feedback, using a three-tier paired text-audio corpus.
-
Reasoning Error from Known Fact: Step-Level Self-Consistency Group Relative Policy Optimization for LLM
SSC-GRPO reweights GRPO advantages using step-level self-consistency judgments to reduce context-sensitive factual hallucinations, with modest average gains across math and hallucination benchmarks.
-
PROBE: Benchmarking Code Generation in Large Language Models
A multi-language evaluation framework measuring correctness, solution proximity, and code quality finds current LLMs pass at most ~0.70 per language and worsen sharply with problem difficulty.
-
Not All Needles Are Found: How Fact Distribution and Don't Make It Up Prompts Shape Retrieval, Reasoning, and Hallucination in Long-Context LLMs
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.
-
Investigating Symbolic Triggers of Hallucination in Gemma Models Across HaluEval and TruthfulQA
Symbolic triggers like modifiers and named entities keep Gemma hallucination rates at 64-79% across model scales, suggesting larger models do not eliminate this failure mode.
-
Sealing The Backdoor: Unlearning Adversarial Text Triggers In Diffusion Models Using Knowledge Distillation
SKD-CAG erases adversarial text triggers from diffusion models by distilling the model's own clean outputs through cross-attention guidance, claiming 100% and 93% removal for pixel and style backdoors.
-
ExploreGS: Explorable 3D Scene Reconstruction with Virtual Camera Samplings and Diffusion Priors
Adding information-gain-selected virtual views refined by video diffusion priors to 3D Gaussian Splatting improves arbitrary-view rendering quality.
-
Mitigating Geospatial Knowledge Hallucination in Large Language Models: Benchmarking and Dynamic Factuality Aligning
A new benchmark called GEOHALUBENCH measures how often LLMs invent, omit, or confuse real-world places and relations, and a dynamic-beta KTO method reduces these errors on the benchmark.
-
RealFactBench: A Benchmark for Evaluating Large Language Models in Real-World Fact-Checking
A new 6K-claim benchmark evaluates LLMs and multimodal LLMs on real-world fact-checking with an explicit 'unknown' option and shows web search and multimodal input improve performance.
-
Teaching with Lies: Curriculum DPO on Synthetic Negatives for Hallucination Detection
Using hallucinated benchmark answers as rejected DPO pairs, ordered by an external fact-checker's grounding score, improves hallucination detection in 1B-3B Llama models.
-
Beyond ROUGE: N-Gram Subspace Features for LLM Hallucination Detection
Singular values of label-grouped n-gram frequency tensors are used as MLP features for hallucination detection, with reported gains on HaluEval that rely on label-aware grouping.
-
Loki's Dance of Illusions: A Comprehensive Survey of Hallucination in Large Language Models
A survey of LLM hallucination research that formalizes hallucination types and argues, via incompleteness and undecidability arguments, that hallucinations cannot be fully eliminated.
-
The Scales of Justitia: A Comprehensive Survey on Safety Evaluation of LLMs
A structured survey of LLM safety evaluation that proposes a why/what/where/how taxonomy and catalogs metrics, datasets, benchmarks, evaluators, and frameworks.
Discussion (0). Sign in to comment.