Search Results for author:
Found 13 papers, 5 papers with code
Conditional Poisson Stochastic Beams
Beam search is the default decoding strategy for many sequence generation tasks in NLP.
The Role of $n$-gram Smoothing in the Age of Neural Networks
For nearly three decades, language models derived from the $n$-gram assumption held the state of the art on the task.
Direct Preference Optimization with an Offset
DPO, as originally formulated, relies on binary preference data and fine-tunes a language model to increase the likelihood of a preferred response over a dispreferred response.
Principled Gradient-based Markov Chain Monte Carlo for Text Generation
Recent papers have demonstrated the possibility of energy-based text generation by adapting gradient-based sampling algorithms, a paradigm of MCMC algorithms that promises fast convergence.
Assessing Large Language Models on Climate Information
We evaluate several recent LLMs and conduct a comprehensive analysis of the results, shedding light on both the potential and the limitations of LLMs in the realm of climate communication.
Which Spurious Correlations Impact Reasoning in NLI Models? A Visual Interactive Diagnosis through Data-Constrained Counterfactuals
We present a human-in-the-loop dashboard tailored to diagnosing potential spurious features that NLI models rely on for predictions.
Hexatagging: Projective Dependency Parsing as Tagging
We introduce a novel dependency parser, the hexatagger, that constructs dependency trees by tagging the words in a sentence with elements from a finite set of possible tags.
Structured Voronoi Sampling
In this paper, we take an important step toward building a principled approach for sampling from language models with gradient-based methods.
Linear-Time Modeling of Linguistic Structure: An Order-Theoretic Perspective
We show that these exhaustive comparisons can be avoided, and, moreover, the complexity of such tasks can be reduced to linear by casting the relation between tokens as a partial order over the string.
In-Context Probing: Toward Building Robust Classifiers via Probing Large Language Models
However, the effectiveness of in-context learning is dependent on the provided context, and the performance on a downstream task can vary considerably, depending on the instruction.
On Parsing as Tagging
There have been many proposals to reduce constituency parsing to tagging in the literature.
Naturalistic Causal Probing for Morpho-Syntax
Probing has become a go-to methodology for interpreting and analyzing deep neural models in natural language processing.
Conditional Poisson Stochastic Beam Search
In this work, we propose a new method for turning beam search into a stochastic process: Conditional Poisson stochastic beam search.
