# Grounding Without Corrective Control: Truth-Tracking Profiles for Large Language Models

arXiv: https://arxiv.org/abs/2608.14252 · HTML: https://mlsanity.com/paper/2608.14252/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 53 references that are in the map.
- First posted on arXiv 14 Aug 2026.

## Builds on (most cited first, 11 of 11)

- [Evaluating Object Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2305.10355/) (2023)
- [A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions](https://mlsanity.com/paper/2311.05232/) (2023)
- [Retrieval Augmentation Reduces Hallucination in Conversation](https://mlsanity.com/paper/2104.07567/) (2021)
- [Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task](https://mlsanity.com/paper/2210.13382/) (2022)
- [The Vector Grounding Problem](https://mlsanity.com/paper/2304.01481/) (2023)
- [How RLHF Amplifies Sycophancy](https://mlsanity.com/paper/2602.01002/) (2026)
- [Do Language Models' Words Refer?](https://mlsanity.com/paper/2308.05576/) (2023)
- [Are Language Models More Like Libraries or Like Librarians? Bibliotechnism, the Novel Reference Problem, and the Attitudes of LLMs](https://mlsanity.com/paper/2401.04854/) (2024)
- [Does Thought Require Sensory Grounding? From Pure Thinkers to Large Language Models](https://mlsanity.com/paper/2408.09605/) (2024)
- [Large language models and linguistic intentionality](https://mlsanity.com/paper/2404.09576/) (2024)
- [Meaning and understanding in large language models](https://mlsanity.com/paper/2310.17407/) (2023)

## Abstract (arXiv)

Recent work suggests that some large language model representations have content or reference. Grounding can secure either without supplying live routes for correction. This paper asks what follows from that gap. An output is answerable when discrepancies can affect what a target- and task-specific arrangement produces, accepts, or withdraws. The arrangement has corrective control only when live, sufficiently independent routes can detect and repair fresh discrepancies. A route profile records which routes constrain the arrangement and how they are related. Those profiles support analysis of truth-tracking: patterned support for representational success. Language models are the pressure case; text-only arrangements provide a task-relative limiting case. Text-trained models inherit patterns of testimony, coherence, and prior correction. Where target-sensitive correction survives training, these can supply derivative answerability (inherited constraint); live answerability is the relation supplied by a current route for fresh discrepancies. Fluent failures should follow when a task requires independently informative access to the facts. Self-consistency, retrieval, tools, code execution, multimodal input, and feedback should help selectively. Route-by-task interactions test the distinctions. The decomposition's empirical burden is to predict held-out route--task combinations or improve intervention choice without conceptual refitting. Surface improvement and truth-tracking improvement can come apart.