The Truth Stays in the Family: Enhancing Contextual Grounding via Inherited Truthful Heads in Model Lineages

• URL: http://arxiv.org/abs/2606.15821v1
• Date: Sun, 14 Jun 2026 13:39:09 GMT
• Title: The Truth Stays in the Family: Enhancing Contextual Grounding via Inherited Truthful Heads in Model Lineages
• Abstract summary: We quantify head-level context-truthfulness scores in large language models.<n>We find that Truth Scores are strongly preserved within model families, even after instruction tuning or multimodal adaptation.<n>We propose TruthProbe, a soft-gating strategy that amplifies context-truthful heads while preserving other head contributions.
• Score: 17.631812310962626
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent advances in large language models (LLMs) have produced many specialized multimodal LLMs (MLLMs) that share common foundational LLMs, forming distinct model lineages. It remains unclear whether a fundamental behavioral link exists between the foundational LLMs and downstream variants. We investigate this question by quantifying head-level context-truthfulness scores. Across diverse LLM and MLLM lineages, including Vicuna-, Qwen2.5-, LLaMA2-, and Mistral-based models, we find that Truth Scores are strongly preserved within model families, even after instruction tuning or multimodal adaptation. We further show that this inheritance is consistent with attention-head weight preservation, and that context-truthful heads attend to query-relevant evidence. Building on this finding, we propose TruthProbe, a soft-gating strategy that amplifies context-truthful heads while preserving other head contributions. TruthProbe improves contextual truthfulness on HaluEval and reduces multimodal hallucination on POPE and CHAIR, with base-LLM Truth Scores transferring effectively to their fine-tuned LLM and MLLM descendants. Code is available at https://github.com/miso-choi/TruthProbe.

Related papers

• What About the Scene with the Hitler Reference? HAUNT: A Framework to Probe LLMs' Self-consistency Via Adversarial Nudge [30.640398600941598]
  Hallucinations pose a critical challenge to the real-world deployment of large language models (LLMs) in high-stakes domains.<n>We present a framework for stress testing factual fidelity in LLMs in the presence of adversarial nudge.
  arXiv  Detail & Related papers  (2025-10-31T02:02:39Z)
• LLM-Lasso: A Robust Framework for Domain-Informed Feature Selection and Regularization [59.75242204923353]
  We introduce LLM-Lasso, a framework that leverages large language models (LLMs) to guide feature selection in Lasso regression.<n>LLMs generate penalty factors for each feature, which are converted into weights for the Lasso penalty using a simple, tunable model.<n>Features identified as more relevant by the LLM receive lower penalties, increasing their likelihood of being retained in the final model.
  arXiv  Detail & Related papers  (2025-02-15T02:55:22Z)
• Investigating Context-Faithfulness in Large Language Models: The Roles of Memory Strength and Evidence Style [13.968658352075334]
  We investigate the impact of memory strength and evidence presentation on Large Language Models' receptiveness to external evidence.<n>Our results show that for questions with high memory strength, LLMs are more likely to rely on internal memory.<n>These findings provide key insights for improving retrieval-augmented generation and context-aware LLMs.
  arXiv  Detail & Related papers  (2024-09-17T07:44:06Z)
• A Probabilistic Framework for LLM Hallucination Detection via Belief Tree Propagation [72.93327642336078]
  We propose Belief Tree Propagation (BTProp), a probabilistic framework for hallucination detection.<n>BTProp introduces a belief tree of logically related statements by decomposing a parent statement into child statements.<n>Our method improves baselines by 3%-9% (evaluated by AUROC and AUC-PR) on multiple hallucination detection benchmarks.
  arXiv  Detail & Related papers  (2024-06-11T05:21:37Z)
• TruthEval: A Dataset to Evaluate LLM Truthfulness and Reliability [0.0]
  We present a curated collection of challenging statements on sensitive topics for benchmarking called TruthEval. These statements were curated by hand and contain known truth values. We perform some initial analyses using this dataset and find several instances of LLMs failing in simple tasks showing their inability to understand simple questions.
  arXiv  Detail & Related papers  (2024-06-04T00:01:35Z)
• Characterizing Truthfulness in Large Language Model Generations with Local Intrinsic Dimension [63.330262740414646]
  We study how to characterize and predict the truthfulness of texts generated from large language models (LLMs) We suggest investigating internal activations and quantifying LLM's truthfulness using the local intrinsic dimension (LID) of model activations.
  arXiv  Detail & Related papers  (2024-02-28T04:56:21Z)
• Assessing the Reliability of Large Language Model Knowledge [78.38870272050106]
  Large language models (LLMs) have been treated as knowledge bases due to their strong performance in knowledge probing tasks. How do we evaluate the capabilities of LLMs to consistently produce factually correct answers? We propose MOdel kNowledge relIabiliTy scORe (MONITOR), a novel metric designed to directly measure LLMs' factual reliability.
  arXiv  Detail & Related papers  (2023-10-15T12:40:30Z)
• Survey on Factuality in Large Language Models: Knowledge, Retrieval and Domain-Specificity [61.54815512469125]
  This survey addresses the crucial issue of factuality in Large Language Models (LLMs) As LLMs find applications across diverse domains, the reliability and accuracy of their outputs become vital.
  arXiv  Detail & Related papers  (2023-10-11T14:18:03Z)
• DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models [79.01926242857613]
  Large language models (LLMs) are prone to hallucinations, generating content that deviates from facts seen during pretraining. We propose a simple decoding strategy for reducing hallucinations with pretrained LLMs. We find that this Decoding by Contrasting Layers (DoLa) approach is able to better surface factual knowledge and reduce the generation of incorrect facts.
  arXiv  Detail & Related papers  (2023-09-07T17:45:31Z)
• The Internal State of an LLM Knows When It's Lying [18.886091925252174]
  Large Language Models (LLMs) have shown exceptional performance in various tasks. One of their most prominent drawbacks is generating inaccurate or false information with a confident tone. We provide evidence that the LLM's internal state can be used to reveal the truthfulness of statements.
  arXiv  Detail & Related papers  (2023-04-26T02:49:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.