REVIEW 11 cited by
Lookback Lens: Detecting and Mitigating Contextual Hallucinations in Large Language Models Using Only Attention Maps
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
Lookback Lens: Detecting and Mitigating Contextual Hallucinations in Large Language Models Using Only Attention Maps
read the original abstract
When asked to summarize articles or answer questions given a passage, large language models (LLMs) can hallucinate details and respond with unsubstantiated answers that are inaccurate with respect to the input context. This paper describes a simple approach for detecting such contextual hallucinations. We hypothesize that contextual hallucinations are related to the extent to which an LLM attends to information in the provided context versus its own generations. Based on this intuition, we propose a simple hallucination detection model whose input features are given by the ratio of attention weights on the context versus newly generated tokens (for each attention head). We find that a linear classifier based on these lookback ratio features is as effective as a richer detector that utilizes the entire hidden states of an LLM or a text-based entailment model. The lookback ratio-based detector -- Lookback Lens -- is found to transfer across tasks and even models, allowing a detector that is trained on a 7B model to be applied (without retraining) to a larger 13B model. We further apply this detector to mitigate contextual hallucinations, and find that a simple classifier-guided decoding approach is able to reduce the amount of hallucination, for example by 9.6% in the XSum summarization task.
Forward citations
Cited by 11 Pith papers
-
All Circuits Lead to Rome: Rethinking Functional Anisotropy in Circuit and Sheaf Discovery for LLMs
LLM tasks are supported by multiple distinct circuits rather than unique mechanisms, demonstrated via Overlap-Aware Sheaf Repulsion and the Distributive Dense Circuit Hypothesis.
-
RAGognizer: Hallucination-Aware Fine-Tuning via Detection Head Integration
RAGognizer adds a detection head to LLMs for joint training on generation and token-level hallucination detection, yielding SOTA detection and fewer hallucinations in RAG while preserving output quality.
-
Does Bielik Know What It Doesn't Know? Activation Dispersion Separates Entity Familiarity from Factual Reliability Across Model Scale
Unsupervised MLP activation dispersion separates known from fabricated entities at AUROC 0.95–1.00 across Bielik scales, while factual reliability scales separately and refusals stay near zero.
-
Hallucination Detection via Activations of Open-Weight Proxy Analyzers
A framework using activation-based features from small open-weight proxy models detects LLM hallucinations with higher AUC than ReDeEP on RAGTruth, performing consistently across seven analyzer architectures.
-
The Surprising Universality of LLM Outputs: A Real-Time Verification Primitive
LLM token rank-frequency distributions converge to a shared Mandelbrot distribution across models and domains, enabling a microsecond-scale statistical primitive for provenance verification and black-box anomaly triage.
-
Adversarial Humanities Benchmark: Results on Stylistic Robustness in Frontier Model Safety
Stylistic rewrites of harmful prompts raise attack success rates from 3.84% to 36.8-65% across 31 frontier models, indicating weak generalization in safety refusals.
-
From Retinal Evidence to Safe Decisions: RETINA-SAFE and ECRT for Hallucination Risk Triage in Medical LLMs
RETINA-SAFE benchmark and ECRT two-stage triage improve hallucination risk detection in medical LLMs for retinal decisions by 0.15-0.19 balanced accuracy over baselines using internal representations and logit shifts.
-
Automated Attention Pattern Discovery at Scale in Large Language Models
AP-MAE reconstructs masked attention patterns in LLMs with high accuracy, generalizes across models, predicts generation correctness at 55-70%, and enables 13.6% accuracy gains via targeted interventions.
-
Towards Dependable Retrieval-Augmented Generation Using Factual Confidence Prediction
A conformal prediction filter for retrieval chunks plus an attention-based factuality classifier can raise RAG answer quality by up to 6% and detect inconsistent generations up to 77% of the time.
-
HalluScan: A Systematic Benchmark for Detecting and Mitigating Hallucinations in Instruction-Following LLMs
HalluScan benchmark tests hallucination detectors on LLMs, identifies NLI Verification as top performer with 0.88 AUROC, and introduces HalluScore (r=0.41 with humans) plus a routing method for 2x cost savings.
-
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.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.