Advancing Understanding, Detection, and Mitigation of LLM Hallucinations

Inference-time truthfulness steering reduces hallucination, but recent work reports that it also weakens refusal of harmful requests. Prior studies count a model response to harmful prompts as a safety failure, without checking whether the response is correct. We ask whether the compliance that truthfulness steering adds is valid. We define valid compliance as the share of requests a model neither refuses nor answers incorrectly, and measure it alongside compliance on tasks that trigger refusal through harmful-sounding wording but have harmless, verifiable answers, with matched harmless controls. We evaluate four steering methods (ITI, TruthX, Contrastive Activation Addition and a representation-engineering direction) on LLaMA-3-8B-Instruct and Llama-2-7B-Chat, calibrating each method on held-out data. On LLaMA-3-8B-Instruct, moderate ITI steering increased refusal, the opposite of the reported effect. Where stronger steering raised compliance, valid compliance fell to under 2%, giving a gap of 44 to 64 percentage points between compliance and valid compliance, and the rise in compliance and unsafe ratings occurred only at strengths that no longer improved truthfulness. On Llama-2-7B-Chat, steering never broke refusal: compliance only fell, while accuracy on harmless controls collapsed. On both models, tuning-set truthfulness gains did not replicate on held-out questions, and TruthX, applied from its authors' released model, did not improve truthfulness in our evaluation. We also show that the labels of a widely used safety classifier, Llama Guard 3, change by tens of percentage points when only the refusal wording of steered replies is edited, on both models, which affects how large a reported safety cost appears.

Authors

Publication Details

Journal
Preprints.org
Published
2026-11-16
DOI
https://doi.org/10.20944/preprints202611.1521.v1
Primary Topic
Adversarial Robustness in Machine Learning
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

Advancing Understanding, Detection, and Mitigation of LLM Hallucinations

Sayanton Vhaduri Dibbo, Adebayo Keji
1 links
Preprints.org
Adversarial Robustness in Machine Learning
preprint

Advancing Understanding, Detection, and Mitigation of LLM Hallucinations

Sayanton Vhaduri Dibbo, Adebayo Keji
preprint en

Abstract

Inference-time truthfulness steering reduces hallucination, but recent work reports that it also weakens refusal of harmful requests. Prior studies count a model response to harmful prompts as a safety failure, without checking whether the response is correct. We ask whether the compliance that truthfulness steering adds is valid. We define valid compliance as the share of requests a model neither refuses nor answers incorrectly, and measure it alongside compliance on tasks that trigger refusal through harmful-sounding wording but have harmless, verifiable answers, with matched harmless controls. We evaluate four steering methods (ITI, TruthX, Contrastive Activation Addition and a representation-engineering direction) on LLaMA-3-8B-Instruct and Llama-2-7B-Chat, calibrating each method on held-out data. On LLaMA-3-8B-Instruct, moderate ITI steering increased refusal, the opposite of the reported effect. Where stronger steering raised compliance, valid compliance fell to under 2%, giving a gap of 44 to 64 percentage points between compliance and valid compliance, and the rise in compliance and unsafe ratings occurred only at strengths that no longer improved truthfulness. On Llama-2-7B-Chat, steering never broke refusal: compliance only fell, while accuracy on harmless controls collapsed. On both models, tuning-set truthfulness gains did not replicate on held-out questions, and TruthX, applied from its authors' released model, did not improve truthfulness in our evaluation. We also show that the labels of a widely used safety classifier, Llama Guard 3, change by tens of percentage points when only the refusal wording of steered replies is edited, on both models, which affects how large a reported safety cost appears.

Preprints.org
Adversarial Robustness in Machine Learning
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon