18 papers
Post-Training Language Models for Crosslingual Consistency
Tianyu Liu, Jirui Qi, Mrinmaya Sachan +3
Language models often respond inconsistently to translation-equivalent prompts across languages, undermining the reliability of multilingual systems. To quantify this, we give an i…
Learning to Reason Efficiently with A* Post-Training
Andreas Opedal, Francesco Ignazio Re, Abulhair Saparov +3
Many applications of large language models (LLMs) require deductive reasoning, yet models frequently produce incorrect or redundant inference steps. We frame natural language infer…
On the Proper Treatment of Units in Surprisal Theory
Samuel Kiegeland, Vésteinn Snæbjarnarson, Tim Vieira +1
Surprisal theory links human processing effort to the predictability of an upcoming linguistic unit, but empirical work often leaves the notion of a unit underspecified. In practic…
Prefix Parsing is Just Parsing
Clemente Pasti, Andreas Opedal, Timothy J. O'Donnell +2
Prefix parsing asks whether an input prefix can be extended to a complete string generated by a given grammar. In the weighted setting, it also provides prefix probabilities, which…
Faster LLM Inference via Sequential Monte Carlo
Yahya Emara, Mauricio Barba da Costa, Chi-Chih Chang +4
Speculative decoding (SD) accelerates language model inference by drafting tokens from a cheap proposal model and verifying them against an expensive target model via rejection sam…
Ensembling Language Models with Sequential Monte Carlo
Robin Shing Moon Chan, Tianyu Liu, Samuel Kiegeland +5
Practitioners have access to an abundance of language models and prompting strategies for solving many language modeling tasks; yet prior work shows that modeling performance is hi…