Search Results for author:
Found 26 papers, 20 papers with code
Beyond Memorization: The Challenge of Random Memory Access in Language Models
Through carefully-designed synthetic tasks, covering the scenarios of full recitation, selective recitation and grounded question answering, we reveal that LMs manage to sequentially access their memory while encountering challenges in randomly accessing memorized content.
Instruction-tuned Language Models are Better Knowledge Learners
The standard recipe for doing so involves continued pre-training on new documents followed by instruction-tuning on question-answer (QA) pairs.
Learning to Filter Context for Retrieval-Augmented Generation
To alleviate these problems, we propose FILCO, a method that improves the quality of the context provided to the generator by (1) identifying useful context based on lexical and information-theoretic approaches, and (2) training context filtering models that can filter retrieved contexts at test time.
Active Retrieval Augmented Generation
In this work, we provide a generalized view of active retrieval augmented generation, methods that actively decide when and what to retrieve across the course of the generation.
From Zero to Hero: Examining the Power of Symbolic Tasks in Instruction Tuning
Empirical results on various benchmarks validate that the integration of SQL execution leads to significant improvements in zero-shot scenarios, particularly in table reasoning.
GPTScore: Evaluate as You Desire
Generative Artificial Intelligence (AI) has enabled the development of sophisticated models that are capable of producing high-caliber text, images, and other outputs through the utilization of large pre-trained models.
Retrieval as Attention: End-to-end Learning of Retrieval and Reading within a Single Transformer
Systems for knowledge-intensive tasks such as open-domain question answering (QA) usually consist of two stages: efficient retrieval of relevant documents from a large corpus and detailed reading of the selected documents to generate answers.
Ranked #1 on
Passage Retrieval
on Natural Questions
SPE: Symmetrical Prompt Enhancement for Fact Probing
In this work, we propose Symmetrical Prompt Enhancement (SPE), a continuous prompt-based method for factual probing in PLMs that leverages the symmetry of the task by constructing symmetrical prompts for subject and object prediction.
Understanding and Improving Zero-shot Multi-hop Reasoning in Generative Question Answering
In sum, these results demonstrate that multi-hop reasoning does not emerge naturally in generative QA models, but can be encouraged by advances in training or modeling techniques.
EditEval: An Instruction-Based Benchmark for Text Improvements
Evaluation of text generation to date has primarily focused on content created sequentially, rather than improvements on a piece of text.
PEER: A Collaborative Language Model
Textual content is often the output of a collaborative writing process: We start with an initial draft, ask for suggestions, and repeatedly make changes.
DocPrompting: Generating Code by Retrieving the Docs
Publicly available source-code libraries are continuously growing and changing.
OmniTab: Pretraining with Natural and Synthetic Data for Few-shot Table-based Question Answering
The information in tables can be an important complement to text, making table-based question answering (QA) systems of great value.
Ranked #7 on
Semantic Parsing
on WikiTableQuestions
Table Retrieval May Not Necessitate Table-specific Model Design
In this work, we focus on the task of table retrieval, and ask: "is table-specific model design necessary for table retrieval, or can a simpler text-based model be effectively used to achieve a similar result?"
Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing
This paper surveys and organizes research works in a new paradigm in natural language processing, which we dub "prompt-based learning".
CoRI: Collective Relation Integration with Data Augmentation for Open Information Extraction
We propose a two-stage Collective Relation Integration (CoRI) model, where the first stage independently makes candidate predictions, and the second stage employs a collective model that accesses all candidate predictions to make globally coherent predictions.
How Can We Know When Language Models Know? On the Calibration of Language Models for Question Answering
We examine this question from the point of view of calibration, the property of a probabilistic model's predicted probabilities actually being well correlated with the probabilities of correctness.
GSum: A General Framework for Guided Neural Abstractive Summarization
Neural abstractive summarization models are flexible and can produce coherent summaries, but they are sometimes unfaithful and can be difficult to control.
X-FACTR: Multilingual Factual Knowledge Retrieval from Pretrained Language Models
We further propose a code-switching-based method to improve the ability of multilingual LMs to access knowledge, and verify its effectiveness on several benchmark languages.
Incorporating External Knowledge through Pre-training for Natural Language to Code Generation
Open-domain code generation aims to generate code in a general-purpose programming language (such as Python) from natural language (NL) intents.
Ranked #3 on
Code Generation
on CoNaLa-Ext
Learning Relation Entailment with Structured and Textual Information
We propose several methods that incorporate both structured and textual information to represent relations for this task.
How Can We Know What Language Models Know?
Recent work has presented intriguing results examining the knowledge contained in language models (LM) by having the LM fill in the blanks of prompts such as "Obama is a _ by profession".
Graph-Revised Convolutional Network
Graph Convolutional Networks (GCNs) have received increasing attention in the machine learning community for effectively leveraging both the content features of nodes and the linkage patterns across graphs in various applications.
Generalizing Natural Language Analysis through Span-relation Representations
Natural language processing covers a wide variety of tasks predicting syntax, semantics, and information content, and usually each type of output is generated with specially designed architectures.
Ranked #1 on
Relation Extraction
on WLPC
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+8
Personalizing Search Results Using Hierarchical RNN with Query-aware Attention
Our analysis reveals that the attention model is able to attribute higher weights to more related past sessions after fine training.
Improving Open Information Extraction via Iterative Rank-Aware Learning
We found that the extraction likelihood, a confidence measure used by current supervised open IE systems, is not well calibrated when comparing the quality of assertions extracted from different sentences.
