Skip to content

Faithful Activation Verbalization: Reducing Hallucinations in LLM Representation Interpretation

Sep 2026 · arXiv.org · Vol abs/2609.34033 · 1 citation · 30 references
Computer Science

TL;DR

A two-stage framework that first reconstructs source text from a hidden activation and then evaluates the resulting text with a separate frozen question-answering model, yielding an explicit and inspectable intermediate readout is introduced, enabling compact cross-model inverters to surpass donor-matched question-conditioned verbalizers while improving both semantic recoverability and lexical fidelity.

Abstract

Activation verbalization methods such as Activation Oracle and Natural Language Autoencoders decode hidden representations of large language models into human-readable natural language. However, existing methods can produce incomplete or hallucinated descriptions, making their activation verbalizations difficult to trust and use reliably in practice. To this end, we introduce AVPO, a two-stage framework that first reconstructs source text from a hidden activation and then evaluates the resulting text with a separate frozen question-answering model, yielding an explicit and inspectable intermediate readout. We further optimize the inverter with direct preference optimization (DPO), using rewards that capture both semantic recoverability and lexical fidelity. Across six text families, AVPO improves gist- and detail-level information recovery over the strongest baseline by up to 17.1 and 9.3 percentage points, respectively. Crucially, the gains arise from preference optimization rather than fine-tuning on selected reconstructions alone, enabling compact cross-model inverters to surpass donor-matched question-conditioned verbalizers while improving both semantic recoverability and lexical fidelity. Moreover, out-of-distribution case study shows that AVPO better recovers high-level semantics while fabricating fewer details.

View source

Similar papers

Review Open access Sep 2026

A SURVEY OF HALLUCINATION MITIGATION STRATEGIES IN LARGE LANGUAGE MODELS: FROM DECODING-TIME FIXES TO AGENTIC RETRIEVAL AND VERIFICATION

Hallucination – the generation of fluent but factually unsupported or fabricated content – remains one of the most persistent obstacles to deploying Large Language Models (LLMs) in high-stakes domains such as healthcare, finance, and law. A wide range of mitigation strategies has been proposed, spanning several distinc...

Shweta Narayan Bamne, M. S. Shegokar · 0 citations
#artificial intelligence Preprint Aug 2026

EviAnchor: Mitigating Hallucinations in Large Vision-Language Models via Regional Visual Evidence Compensation

EviAnchor is proposed, a training-free and single-branch inference framework that preserves and reactivates visual evidence throughout generation in large vision-language models and demonstrates consistent improvements in visual grounding.

Sihang Jia, Shu-Liang Liu, Song-Bo Yang et al. · 0 citations
#natural language process... Preprint Sep 2026

The Anatomy of an ASR Hallucination

This work identifies a mechanistic precondition for hallucination - the failure to produce adequately grounded output - not the complete origin of naturally occurring hallucination - not the complete origin of naturally occurring hallucinations.

H. Sayed, Apoorv Singh, Kumar Aman et al. · 0 citations
Open access Sep 2026

Large Language Models Create Hallucinations in Response to Negated Text

It is demonstrated that LLMs struggle to handle negation effectively, applying affirmative knowledge inappropriately, leading to hallucinations that contradict the negated input, compromising the logical consistency and factual accuracy of LLM outputs.

Jaehyung Seo, Hyeonseok Moon, Heu-Jeoung Lim · 0 citations
#artificial intelligence Preprint Sep 2026

Domain-Specific Hallucination Detection in Large Language Models

A multi-signal detection pipeline combining fine-tuned DeBERTa-v3 classification, Monte Carlo Dropout uncertainty quantification, and temperature-scaled calibration for response-level hallucination detection is presented.

Varun Teja Chundru, Debasmita Biswas · 0 citations
Sep 2026

SAVOR: Self-Aware Visual Grounding via Confidence-Calibrated Reinforcement Learning for Multimodal Hallucination Mitigation

Savor is introduced, a training framework that augments the output schema with token and answer confidence, optimises the policy with a Group Relative Policy Optimisation objective that penalises calibration error and poor abstention decisions, and uses the learned confidence at inference time to revisit visual evidenc...

Zian Ding, Zi-Lin Zhao, Ying-Jie He et al. · 0 citations

Related blog posts

MIT News · Artificial Intelligence Nov 17, 2026

Learning the language of machine learning

By studying the computational foundations of language learning, Associate Professor Jacob Andreas builds intelligent systems that can communicate effectively with humans.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.