FLAS learns a multi-step velocity field v_t(h,t,c) to steer activations, outperforming prompting with harmonic means of 1.015 and 1.113 on two Gemma models without per-concept tuning.
Steer llm latents for hallucination detection
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
abstract
Hallucinations in LLMs pose a significant concern to their safe deployment in real-world applications. Recent approaches have leveraged the latent space of LLMs for hallucination detection, but their embeddings, optimized for linguistic coherence rather than factual accuracy, often fail to clearly separate truthful and hallucinated content. To this end, we propose the Truthfulness Separator Vector (TSV), a lightweight and flexible steering vector that reshapes the LLM's representation space during inference to enhance the separation between truthful and hallucinated outputs, without altering model parameters. Our two-stage framework first trains TSV on a small set of labeled exemplars to form compact and well-separated clusters. It then augments the exemplar set with unlabeled LLM generations, employing an optimal transport-based algorithm for pseudo-labeling combined with a confidence-based filtering process. Extensive experiments demonstrate that TSV achieves state-of-the-art performance with minimal labeled data, exhibiting strong generalization across datasets and providing a practical solution for real-world LLM applications.
fields
cs.CL 4representative citing papers
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.
REALISTA generates semantically coherent adversarial prompts via latent-space optimization over input-dependent editing directions, achieving stronger hallucination elicitation than prior realistic attacks on open-source and reasoning LLMs.
By steering activations along directions learned from base-vs-fine-tuned disagreements, REFLEX reports 64.99 macro-F1 on RAW-FC fact-checking with only ~465 self-refined contrastive samples and no retrieval.
citing papers explorer
-
Beyond Steering Vector: Flow-based Activation Steering for Inference-Time Intervention
FLAS learns a multi-step velocity field v_t(h,t,c) to steer activations, outperforming prompting with harmonic means of 1.015 and 1.113 on two Gemma models without per-concept tuning.
-
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.
-
REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations
REALISTA generates semantically coherent adversarial prompts via latent-space optimization over input-dependent editing directions, achieving stronger hallucination elicitation than prior realistic attacks on open-source and reasoning LLMs.
-
REFLEX: Self-Refining Explainable Fact-Checking via Verdict-Anchored Style Control
By steering activations along directions learned from base-vs-fine-tuned disagreements, REFLEX reports 64.99 macro-F1 on RAW-FC fact-checking with only ~465 self-refined contrastive samples and no retrieval.