From decoding to meta-generation: Inference-time algorithms for large language models

S Welleck, A Bertsch, M Finlayson… - arxiv preprint arxiv …, 2024 - arxiv.org
One of the most striking findings in modern research on large language models (LLMs) is
that scaling up compute during training leads to better results. However, less attention has …

K⁎: A heuristic search algorithm for finding the k shortest paths

H Aljazzar, S Leue - Artificial Intelligence, 2011 - Elsevier
We present a directed search algorithm, called K⁎, for finding the k shortest paths between a
designated pair of vertices in a given directed weighted graph. K⁎ has two advantages …

If the current clique algorithms are optimal, so is Valiant's parser

A Abboud, A Backurs, VV Williams - SIAM Journal on Computing, 2018 - SIAM
The CFG recognition problem is as follows: given a context-free grammar G and a string w of
length n, decide whether w can be obtained from G. This is the most basic parsing question …

Imitation learning of agenda-based semantic parsers

J Berant, P Liang - Transactions of the Association for Computational …, 2015 - direct.mit.edu
Semantic parsers conventionally construct logical forms bottom-up in a fixed order, resulting
in the generation of many extraneous partial logical forms. In this paper, we combine ideas …

Dyna: Extending datalog for modern AI

J Eisner, NW Filardo - International Datalog 2.0 Workshop, 2010 - Springer
Modern statistical AI systems are quite large and complex; this interferes with research,
development, and education. We point out that most of the computation involves database …

[BUCH][B] Text analysis pipelines: towards ad-hoc large-scale text mining

H Wachsmuth - 2015 - books.google.com
This monograph proposes a comprehensive and fully automatic approach to designing text
analysis pipelines for arbitrary information needs that are optimal in terms of run-time …

Global neural CCG parsing with optimality guarantees

K Lee, M Lewis, L Zettlemoyer - arxiv preprint arxiv:1607.01432, 2016 - arxiv.org
We introduce the first global recursive neural parsing model with optimality guarantees
during decoding. To support global features, we give up dynamic programs and instead …

-best enumeration

D Eppstein - arxiv preprint arxiv:1412.5075, 2014 - arxiv.org
arxiv:1412.5075v1 [cs.DS] 16 Dec 2014 Page 1 arxiv:1412.5075v1 [cs.DS] 16 Dec 2014 K-Best
Enumeration David Eppstein∗ Abstract We survey k-best enumeration problems and the …

On Finding the -best Non-projective Dependency Trees

R Zmigrod, T Vieira, R Cotterell - arxiv preprint arxiv:2106.00780, 2021 - arxiv.org
The connection between the maximum spanning tree in a directed graph and the best
dependency tree of a sentence has been exploited by the NLP community. However, for …

[PDF][PDF] Efficient inference through cascades of weighted tree transducers

J May, K Knight, H Vogler - … of the 48th Annual Meeting of the …, 2010 - aclanthology.org
Weighted tree transducers have been proposed as useful formal models for representing
syntactic natural language processing applications, but there has been little description of …