Walk the Talk? Measuring the Faithfulness of Large Language Model Explanations · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2504.14150/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTWalk the Talk? Measuring the Faithfulness of Large Language Model Explanations — mentioned by famouswaffleshttps://news.ycombinator.com/item?id=47805537urn:hackerpapers:mention:2504.14150:47805537Fri, 17 Apr 2026 13:08:44 GMT<p>Explanations can be faithful sometimes. That&#x27;s the standard we can expect for any intelligence as far as we&#x27;re aware. https://arxiv.org/abs/2504.14150</p><p><a href="https://hackerpaper.kaipfister.de/p/2504.14150/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CL