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.
By Qinglan Luo, S M A Nahian, John Guttag, S. Mazdak Abulnaga, Katie Matton
arXiv:2606. 28615v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed in high-stakes domains, where free-text explanations such as chain-of-thought and post-hoc rationales are used to justify model outputs.
By Nhi Nguyen, Shauli Ravfogel, Rajesh Ranganath
arXiv:2607. 21090v1 Announce Type: cross Abstract: We propose a Reinforcement Learning (RL) method to directly optimize the faithfulness of self-explanations - the extent to which a model's generated reasoning accurately reflects its internal decision-making process.
By Yeoktatt Cheah, Mar\'ia P\'erez-Ortiz, Noah Y. Siegel, Oana-Maria Camburu
arXiv:2606. 16110v1 Announce Type: new Abstract: Machine unlearning has been extensively studied in response to growing privacy concerns and regulatory requirements.
By Dayong Ye, Tianqing Zhu, Ruiding Huang, Xinbo Fu, Jiayang Li, Bo Liu, Huan Huo, Wanlei Zhou
Machine unlearning has been extensively studied in response to growing privacy concerns and regulatory requirements. However, auditing whether unlearning algorithms have truly erased the influence of specific data remains an open challenge.
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.
By Bonan Shen, Dingyan Shang, Youting Wang, Tao Ning
arXiv:2605. 00994v2 Announce Type: replace-cross Abstract: Finetuning can significantly modify the behavior of large language models, including introducing harmful or unsafe behaviors.
By Mohammed Abu Baker, Luca Baroni, Dan Wilhelm
The paper introduces a method for identifying the dominant knowledge source behind large language model (LLM) outputs, distinguishing between faithfulness violations (misuse of provided context) and factuality violations (errors in internal knowledge). A simple linear probe trained on hidden representations can reliably classify this source, and the authors present AttriWiki, a self‑supervised pipeline that generates labeled training data by prompting models to recall withheld entities or read them from context. Probes trained on AttriWiki achieve high Macro‑F1 scores across several models and datasets, generalize zero‑shot to a benchmark, and show that attribution mismatches can increase error rates by up to 70%.
"whyItMatters":"The study demonstrates that knowing the source of an LLM’s answer is crucial for effective mitigation of hallucinations, as attribution mismatches significantly raise error rates."
By Ivo Brink, Alexander Boer, Dennis Ulmer
arXiv:2503. 13445v3 Announce Type: replace-cross Abstract: When asked to explain their decisions, LLMs can often give explanations which sound plausible to humans.
By Noah Y. Siegel, Nicolas Heess, Maria Perez-Ortiz, Oana-Maria Camburu
arXiv:2608.30581v1 Announce Type: new
Abstract: Large language models (LLMs) are used as post hoc explainers of sequential decision-making policies, producing natural-language explanations of why an...
By Dennis Gross, Helge Spieker
arXiv:2607. 19355v1 Announce Type: new Abstract: LLMs are increasingly used with external knowledge sources like the internet.
By Joshua Ashkinaze, Laura Kurek, Alina Faisal, Tongyuan Miao, Mariam Joseph, Ceren Budak, Eric Gilbert
The paper discusses how large language models (LLMs) can be fine‑tuned with observational data to improve alignment with human preferences and business goals. It highlights that directly using such data can cause models to learn spurious correlations, and introduces DeconfoundLM, a method that removes known confounders from reward signals. Experiments show that DeconfoundLM better recovers causal relationships and outperforms baseline methods by over 16% in objective score when confounding is present.
By Erfan Loghmani