Search Results for author:
Found 26 papers, 17 papers with code
LAIT: Efficient Multi-Segment Encoding in Transformers with Layer-Adjustable Interaction
Transformer encoders contextualize token representations by attending to all other tokens at each layer, leading to quadratic increase in compute effort with the input length.
PropSegmEnt: A Large-Scale Corpus for Proposition-Level Segmentation and Entailment Recognition
As these propositions can carry different truth values in the context of a given premise, we argue for the need to recognize the textual entailment relation of each proposition in a sentence individually.
Attributed Question Answering: Evaluation and Modeling for Attributed Large Language Models
We take human annotations as a gold standard and show that a correlated automatic metric is suitable for development.
Is margin all you need? An extensive empirical study of active learning on tabular data
Given a labeled training set and a collection of unlabeled data, the goal of active learning (AL) is to identify the best unlabeled points to label.
Conformal Risk Control
We extend conformal prediction to control the expected value of any monotone loss function.
Confident Adaptive Language Modeling
Recent advances in Transformer-based large language models (LLMs) have led to significant performance improvements across many tasks.
Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
BIG-bench focuses on tasks that are believed to be beyond the capabilities of current language models.
UL2: Unifying Language Learning Paradigms
Our model also achieve strong results at in-context learning, outperforming 175B GPT-3 on zero-shot SuperGLUE and tripling the performance of T5-XXL on one-shot summarization.
Ranked #7 on
Long-range modeling
on SCROLLS
Stretching Sentence-pair NLI Models to Reason over Long Documents and Clusters
Natural Language Inference (NLI) has been extensively studied by the NLP community as a framework for estimating the semantic relation between sentence pairs.
Conformal Prediction Sets with Limited False Positives
We propose to trade coverage for a notion of precision by enforcing that the presence of incorrect candidates in the predicted conformal sets (i. e., the total number of false positives) is bounded according to a user-specified tolerance.
Tomayto, Tomahto. Beyond Token-level Answer Equivalence for Question Answering Evaluation
The predictions of question answering (QA)systems are typically evaluated against manually annotated finite sets of one or more answers.
Transformer Memory as a Differentiable Search Index
In this paper, we demonstrate that information retrieval can be accomplished with a single Transformer, in which all information about the corpus is encoded in the parameters of the model.
ExT5: Towards Extreme Multi-Task Scaling for Transfer Learning
Despite the recent success of multi-task learning and transfer learning for natural language processing (NLP), few works have systematically studied the effect of scaling up the number of tasks during pre-training.
Trading Coverage for Precision: Conformal Prediction with Limited False Discoveries
In this paper, we develop a new approach to conformal prediction in which we aim to output a precise set of promising prediction candidates that is guaranteed to contain a limited number of incorrect answers.
Programming Puzzles
The dataset is comprehensive in that it spans problems of a range of difficulties and domains, ranging from trivial string manipulation problems, to classic programming puzzles (e. g., Tower of Hanoi), to interview/competitive-programming problems (e. g., dynamic programming), to longstanding open problems in algorithms and mathematics (e. g., factoring).
Consistent Accelerated Inference via Confident Adaptive Transformers
In this work, we present CATs -- Confident Adaptive Transformers -- in which we simultaneously increase computational efficiency, while guaranteeing a specifiable degree of consistency with the original model with high confidence.
Get Your Vitamin C! Robust Fact Verification with Contrastive Evidence
Typical fact verification models use retrieved written evidence to verify claims.
Few-shot Conformal Prediction with Auxiliary Tasks
We develop a novel approach to conformal prediction when the target task has limited data available for training.
Efficient Conformal Prediction via Cascaded Inference with Expanded Admission
This set is guaranteed to contain a correct answer with high probability, and is well-suited for many open-ended classification tasks.
Distilling the Evidence to Augment Fact Verification Models
We propose, instead, a model-agnostic framework that consists of two modules: (1) a span extractor, which identifies the crucial information connecting claim and evidence; and (2) a classifier that combines claim, evidence, and the extracted spans to predict the veracity of the claim.
Humpty Dumpty: Controlling Word Meanings via Corpus Poisoning
Word embeddings, i. e., low-dimensional vector representations such as GloVe and SGNS, encode word "meaning" in the sense that distances between words' vectors correspond to their semantic proximity.
Automatic Fact-guided Sentence Modification
This is a challenging constrained generation task, as the output must be consistent with the new information and fit into the rest of the existing document.
The Limitations of Stylometry for Detecting Machine-Generated Fake News
Recent developments in neural language models (LMs) have raised concerns about their potential misuse for automatically spreading misinformation.
Towards Debiasing Fact Verification Models
Fact verification requires validating a claim in the context of evidence.
Cross-Lingual Alignment of Contextual Word Embeddings, with Applications to Zero-shot Dependency Parsing
We introduce a novel method for multilingual transfer that utilizes deep contextual embeddings, pretrained in an unsupervised fashion.
Cross-lingual zero-shot dependency parsing
Few-Shot Learning
+1
Optical Flow Requires Multiple Strategies (but only one network)
This type of training produces a network that displays multiple strategies depending on the input and leads to state of the art results on the KITTI 2012 and KITTI 2015 optical flow benchmarks.
