Skip to content [2402.13213] Probabilities of Chat LLMs Are Miscalibrated but Still Predict Correctness on Multiple-Choice Q&A
![[2402.13213] Probabilities of Chat LLMs Are Miscalibrated but Still Predict Correctness on Multiple-Choice Q&A](https://i0.wp.com/arxiv.org/static/browse/0.3.4/images/arxiv-logo-fb.png?w=1920&resize=1920,1113&ssl=1 "[2402.13213] Probabilities of Chat LLMs Are Miscalibrated but Still Predict Correctness on Multiple-Choice Q&A"){kind=logo}
[Submitted on 20 Feb 2024 (v1), last revised 19 Mar 2025 (this version, v3)] View a PDF of the paper ...
Read more MoonCast: High-Quality Zero-Shot Podcast Generation
arXiv:2503.14345v1 Announce Type: cross Abstract: Recent advances in text-to-speech synthesis have achieved notable success in generating high-quality short utterances for ...
Read more Clock and Calendar Understanding Challenges in Multimodal LLMs
[Submitted on 7 Feb 2025 (v1), last revised 18 Mar 2025 (this version, v2)] View a PDF of the paper ...
Read more Min-p Sampling for Creative and Coherent LLM Outputs
[Submitted on 1 Jul 2024 (v1), last revised 16 Mar 2025 (this version, v3)] View a PDF of the paper ...
Read more a Tool for Fine-Grained Machine-Generated Text Detection
[Submitted on 8 Aug 2024 (v1), last revised 14 Mar 2025 (this version, v3)] Authors:Mervat Abassy, Kareem Elozeiri, Alexander Aziz, ...
Read more [2502.17308] Implicit Word Reordering with Knowledge Distillation for Cross-Lingual Dependency Parsing
[Submitted on 24 Feb 2025 (v1), last revised 14 Mar 2025 (this version, v2)] View a PDF of the paper ...
Read more [2503.09701] Have LLMs Made Active Learning Obsolete? Surveying the NLP Community
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals ...
Read more [2501.14073] LLMs are Vulnerable to Malicious Prompts Disguised as Scientific Language
![[2402.13213] Probabilities of Chat LLMs Are Miscalibrated but Still Predict Correctness on Multiple-Choice Q&A](https://i0.wp.com/arxiv.org/static/browse/0.3.4/images/arxiv-logo-fb.png?w=1200&resize=1200,700&ssl=1 "[2402.13213] Probabilities of Chat LLMs Are Miscalibrated but Still Predict Correctness on Multiple-Choice Q&A"){kind=logo}
[Submitted on 23 Jan 2025 (v1), last revised 18 Feb 2025 (this version, v2)] View a PDF of the paper ...
Read more Consuming Resource via Auto-generation for LLM-DoS Attack under Black-box Settings
[Submitted on 18 Dec 2024 (v1), last revised 18 Feb 2025 (this version, v3)] View a PDF of the paper ...
Read more A Review of Tools & Resources
[Submitted on 24 Jun 2024 (v1), last revised 17 Feb 2025 (this version, v4)] Authors:Shayne Longpre, Stella Biderman, Alon Albalak, ...
Read more ![[2402.13213] Probabilities of Chat LLMs Are Miscalibrated but Still Predict Correctness on Multiple-Choice Q&A](https://i0.wp.com/arxiv.org/static/browse/0.3.4/images/arxiv-logo-fb.png?w=150&resize=150,150&ssl=1 "[2402.13213] Probabilities of Chat LLMs Are Miscalibrated but Still Predict Correctness on Multiple-Choice Q&A"){kind=logo}
