Zobrazeno 1 - 10
of 235
pro vyhledávání: '"Koller, Alexander"'
Autor:
Hartmann, Mareike, Koller, Alexander
Goal-directed interactive agents, which autonomously complete tasks through interactions with their environment, can assist humans in various domains of their daily lives. Recent advances in large language models (LLMs) led to a surge of new, more an
Externí odkaz:
http://arxiv.org/abs/2409.18538
We introduce Modelizer - a novel framework that, given a black-box program, learns a _model from its input/output behavior_ using _neural machine translation_. The resulting model _mocks_ the original program: Given an input, the model predicts the o
Externí odkaz:
http://arxiv.org/abs/2407.08597
Models need appropriate inductive biases to effectively learn from small amounts of data and generalize systematically outside of the training distribution. While Transformers are highly versatile and powerful, they can still benefit from enhanced st
Externí odkaz:
http://arxiv.org/abs/2407.04543
Publikováno v:
EMNLP2024
Discourse Representation Theory (DRT) distinguishes itself from other semantic representation frameworks by its ability to model complex semantic and discourse phenomena through structural nesting and variable binding. While seq2seq models hold the s
Externí odkaz:
http://arxiv.org/abs/2407.01899
Autor:
Bavaresco, Anna, Bernardi, Raffaella, Bertolazzi, Leonardo, Elliott, Desmond, Fernández, Raquel, Gatt, Albert, Ghaleb, Esam, Giulianelli, Mario, Hanna, Michael, Koller, Alexander, Martins, André F. T., Mondorf, Philipp, Neplenbroek, Vera, Pezzelle, Sandro, Plank, Barbara, Schlangen, David, Suglia, Alessandro, Surikuchi, Aditya K, Takmaz, Ece, Testoni, Alberto
There is an increasing trend towards evaluating NLP models with LLM-generated judgments instead of human judgments. In the absence of a comparison against human data, this raises concerns about the validity of these evaluations; in case they are cond
Externí odkaz:
http://arxiv.org/abs/2406.18403
We present a method for rewriting an input sentence to match specific values of nontrivial linguistic features, such as dependency depth. In contrast to earlier work, our method uses in-context learning rather than finetuning, making it applicable in
Externí odkaz:
http://arxiv.org/abs/2406.11338
Collaboration is an integral part of human dialogue. Typical task-oriented dialogue games assign asymmetric roles to the participants, which limits their ability to elicit naturalistic role-taking in collaboration and its negotiation. We present a no
Externí odkaz:
http://arxiv.org/abs/2406.08202
LLMs are being increasingly used for planning-style tasks, but their capabilities for planning and reasoning are poorly understood. We present AutoPlanBench, a novel method for automatically converting planning benchmarks written in PDDL into textual
Externí odkaz:
http://arxiv.org/abs/2311.09830
Autor:
Yao, Yuekun, Koller, Alexander
The ability to predict an NLP model's accuracy on unseen, potentially out-of-distribution data is a prerequisite for trustworthiness. We present a novel model that establishes upper and lower bounds on the accuracy, without requiring gold labels for
Externí odkaz:
http://arxiv.org/abs/2311.09422
Autor:
Prasad, Archiki, Koller, Alexander, Hartmann, Mareike, Clark, Peter, Sabharwal, Ashish, Bansal, Mohit, Khot, Tushar
Large Language Models (LLMs) are increasingly being used for interactive decision-making tasks requiring planning and adapting to the environment. Recent works employ LLMs-as-agents in broadly two ways: iteratively determining the next action (iterat
Externí odkaz:
http://arxiv.org/abs/2311.05772