Search Results for author:
Found 22 papers, 15 papers with code
GenAudit: Fixing Factual Errors in Language Model Outputs with Evidence
We present GenAudit -- a tool intended to assist fact-checking LLM responses for document-grounded tasks.
USB: A Unified Summarization Benchmark Across Tasks and Domains
While the NLP community has produced numerous summarization benchmarks, none provide the rich annotations required to simultaneously address many important problems related to control and reliability.
Self-Refine: Iterative Refinement with Self-Feedback
Motivated by how humans refine their written text, we introduce Self-Refine, an approach for improving initial outputs from LLMs through iterative feedback and refinement.
Using In-Context Learning to Improve Dialogue Safety
For instance, using automatic evaluation, we find our best fine-tuned baseline only generates safe responses to unsafe dialogue contexts from DiaSafety 4. 04% more than our approach.
Understanding the Effectiveness of Very Large Language Models on Dialog Evaluation
The paper shows that the choice of datasets used for training a model contributes to how well it performs on a task as well as on how the prompt should be structured.
DialGuide: Aligning Dialogue Model Behavior with Developer Guidelines
These guidelines provide information about the context they are applicable to and what should be included in the response, allowing the models to generate responses that are more closely aligned with the developer's expectations and intent.
InstructDial: Improving Zero and Few-shot Generalization in Dialogue through Instruction Tuning
We introduce InstructDial, an instruction tuning framework for dialogue, which consists of a repository of 48 diverse dialogue tasks in a unified text-to-text format created from 59 openly available dialogue datasets.
Target-Guided Dialogue Response Generation Using Commonsense and Data Augmentation
Target-guided response generation enables dialogue systems to smoothly transition a conversation from a dialogue context toward a target sentence.
DialFact: A Benchmark for Fact-Checking in Dialogue
Fact-checking is an essential tool to mitigate the spread of misinformation and disinformation.
Synthesizing Adversarial Negative Responses for Robust Response Ranking and Evaluation
Experiments on classification, ranking and evaluation tasks across multiple datasets demonstrate that our approaches outperform strong baselines in providing informative negative examples for training dialogue systems.
Obtaining Better Static Word Embeddings Using Contextual Embedding Models
The advent of contextual word embeddings -- representations of words which incorporate semantic and syntactic information from their context -- has led to tremendous improvements on a wide variety of NLP tasks.
Lightweight Cross-Lingual Sentence Representation Learning
Large-scale models for learning fixed-dimensional cross-lingual sentence representations like LASER (Artetxe and Schwenk, 2019b) lead to significant improvement in performance on downstream tasks.
Controlling Dialogue Generation with Semantic Exemplars
Dialogue systems pretrained with large language models generate locally coherent responses, but lack the fine-grained control over responses necessary to achieve specific goals.
Using Image Captions and Multitask Learning for Recommending Query Reformulations
Interactive search sessions often contain multiple queries, where the user submits a reformulated version of the previous query in response to the original results.
Robust Cross-lingual Embeddings from Parallel Sentences
Recent advances in cross-lingual word embeddings have primarily relied on mapping-based methods, which project pretrained word embeddings from different languages into a shared space through a linear transformation.
Cross-Lingual Document Classification
Cross-Lingual Word Embeddings
+7
Investigating Evaluation of Open-Domain Dialogue Systems With Human Generated Multiple References
The aim of this paper is to mitigate the shortcomings of automatic evaluation of open-domain dialog systems through multi-reference evaluation.
WriterForcing: Generating more interesting story endings
In this paper, we propose models which generate more diverse and interesting outputs by 1) training models to focus attention on important keyphrases of the story, and 2) promoting generation of non-generic words.
Better Word Embeddings by Disentangling Contextual n-Gram Information
Pre-trained word vectors are ubiquitous in Natural Language Processing applications.
Online Diverse Learning to Rank from Partial-Click Feedback
We assume that the user examines the list of recommended items until the user is attracted by an item, which is clicked, and does not examine the rest of the items.
Learning Word Vectors for 157 Languages
Distributed word representations, or word vectors, have recently been applied to many tasks in natural language processing, leading to state-of-the-art performance.
Ranked #12 on
Only Connect Walls Dataset Task 1 (Grouping)
on OCW
(using extra training data)
Saliency Prediction for Mobile User Interfaces
However, given the difference in what constitutes a mobile interface, and the usage context of these devices, we postulate that saliency prediction for mobile interface images requires a fresh approach.
Unsupervised Learning of Sentence Embeddings using Compositional n-Gram Features
The recent tremendous success of unsupervised word embeddings in a multitude of applications raises the obvious question if similar methods could be derived to improve embeddings (i. e. semantic representations) of word sequences as well.
