The paper introduces Grammar‑Aligned Decoding (GAD), addressing the issue that conventional grammar‑constrained decoding (GCD) can distort a large language model’s probability distribution, yielding grammatical but low‑likelihood outputs. GAD proposes an adaptive sampling method, Approximate Expected Futures (ASAp), which uses prior samples to over‑approximate future grammaticality, ensuring outputs remain both grammatical and faithful to the model’s conditional probabilities. Experiments on code generation and structured NLP tasks demonstrate that ASAp often produces higher‑likelihood outputs than existing GCD techniques while still enforcing the required grammatical constraints.
By Kanghee Park, Jiayu Wang, Taylor Berg-Kirkpatrick, Nadia Polikarpova, Loris D'Antoni
arXiv:2607. 20286v1 Announce Type: cross Abstract: We propose a novel framework for computing rigorous bounds on the probability that a large language model (LLM) generates harmful output to a given prompt.
By Mahdi Nazeri, Anne-Kathrin Schmuck, Sadegh Soudjani, Alessandro Abate
arXiv:2607. 05995v1 Announce Type: cross Abstract: We propose a novel approach to mine patterns in spatio-temporal event data based on discovering frequent closed embedded sub-Directed Acyclic Graphs (DAGs).
By Piotr S. Maci\k{a}g
arXiv:2602. 17001v3 Announce Type: replace Abstract: Natural Language Querying for Time Series Databases (NLQ4TSDB) aims to assist non-expert users retrieve meaningful events, intervals, and summaries from massive temporal records.
By Zhao Tan, Yiji Zhao, Shiyu Wang, Chang Xu, Yuxuan Liang, Xiping Liu, Shirui Pan, Ming Jin
arXiv:2606. 11235v1 Announce Type: new Abstract: A key step in knowledge discovery is the evaluation of data mining results.
By Leonardo Pellegrina, Fabio Vandin
arXiv:2603.01243v3 Announce Type: replace
Abstract: Large language models (LLMs) are powerful tools that have found applications beyond human-machine interfaces and chatbots. Beside free-form generat...
By Ayoub Hammal, Pierre Zweigenbaum, Caio Corro