arXiv:2607. 04572v2 Announce Type: replace Abstract: Large language model (LLM) tutors may have access to teacher notes, answer keys, rubrics, or retrieved solutions while producing student-facing explanations.
arXiv:2607. 04572v1 Announce Type: new Abstract: Large language model (LLM) tutors often produce fluent step-by-step explanations, but a correct and pedagogically formatted response does not guarantee that the answer was derived from the student-facing problem.
The paper proposes a test‑time method to enhance the faithfulness of large language model (LLM) explanations by removing concepts not credited in the model’s explanation before re‑querying the model. This approach targets incompleteness—omissions of influential factors—rather than unsoundness, and is model‑agnostic, requiring no changes to model weights. Experiments across two datasets and multiple model families show improved faithfulness compared to standard prompting and faithfulness‑encouraging prompts.
arXiv:2606. 24267v1 Announce Type: cross Abstract: While in-context learning is generally shown to be effective in Large Language Models (LLMs), bad contexts can cause performance degradation and mode collapse, a phenomenon we call "pigeonholing.
arXiv:2606. 24267v2 Announce Type: replace-cross Abstract: While in-context learning is generally shown to be effective in Large Language Models (LLMs), bad contexts can cause performance degradation and mode collapse, a phenomenon we call "pigeonholing.
The paper investigates whether giving AI monitors access to the final answer improves their ability to verify reasoning. Using 237 step‑by‑step solutions to physics exam questions, the authors found that answer access mainly helps monitors detect inconsistencies with the final answer rather than independently checking the reasoning. Certification of the answer increased overall accuracy and error localization but reduced the ability to flag critical traces where the answer was correct but the reasoning was flawed.
arXiv:2607. 22629v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) produce long, explicit chains of intermediate steps before generating a final answer at inference time.
arXiv:2606. 00642v1 Announce Type: new Abstract: Reasoning traces have become a valuable form of learning signals for improving and transferring the capabilities of large language models.
arXiv:2607.23458v2 Announce Type: replace Abstract: Chain-of-thought (CoT) explanations support oversight only if they are faithful: the stated reasoning must actually produce the answer. Auditing bl...
arXiv:2606. 05625v1 Announce Type: cross Abstract: Implicit reward hacking is hard to audit when a language model's chain of thought appears benign: a final answer may be anchored by a prompt shortcut while the written reasoning still resembles ordinary problem solving.
The paper proposes a test‑time method to enhance the faithfulness of large language model (LLM) explanations by removing concepts that are not credited in the model’s explanation before re‑querying the model. This approach directly addresses the incompleteness dimension of unfaithful explanations, unlike prior methods that mainly target unsoundness. Experiments across two datasets, multiple model families, and two faithfulness metrics show that the method improves explanation faithfulness over standard prompting and faithfulness‑encouraging prompts, and it is model‑agnostic and requires no parameter changes.
arXiv:2607. 08173v1 Announce Type: new Abstract: Black box auditing of language models is an essential pre-deployment tool, but it may miss subtle forms of misalignment and hidden information.
arXiv:2607. 20379v1 Announce Type: new Abstract: Natural-language autoencoders score explanations of hidden activations by reconstruction: an explanation is deemed faithful if the activation can be regenerated from it.