Search Results for author:
Found 40 papers, 26 papers with code
Offset Unlearning for Large Language Models
Despite the strong capabilities of Large Language Models (LLMs) to acquire knowledge from their training corpora, the memorization of sensitive information in the corpora such as copyrighted, harmful, and private content has led to ethical and legal concerns.
Contrastive Instruction Tuning
Instruction tuning has been used as a promising approach to improve the performance of large language models (LLMs) on unseen tasks.
GeoLM: Empowering Language Models for Geospatially Grounded Language Understanding
This paper introduces GeoLM, a geospatially grounded language model that enhances the understanding of geo-entities in natural language.
Reinforcement Learning in a Safety-Embedded MDP with Trajectory Optimization
This work introduces a novel approach that combines RL with trajectory optimization to manage this trade-off effectively.
UniversalNER: Targeted Distillation from Large Language Models for Open Named Entity Recognition
Instruction tuning has proven effective for distilling LLMs into more cost-efficient models such as Alpaca and Vicuna.
Ranked #1 on
Named Entity Recognition (NER)
on NCBI Disease
Robust Natural Language Understanding with Residual Attention Debiasing
However, previous ensemble-based debiasing methods typically apply debiasing on top-level logits without directly addressing biased attention patterns.
A Causal View of Entity Bias in (Large) Language Models
Building upon this SCM, we propose causal intervention techniques to mitigate entity bias for both white-box and black-box settings.
Getting Sick After Seeing a Doctor? Diagnosing and Mitigating Knowledge Conflicts in Event Temporal Reasoning
However, knowledge conflicts arise when there is a mismatch between the actual temporal relations of events in the context and the prior knowledge or biases learned by the model.
How Fragile is Relation Extraction under Entity Replacements?
In principle, textual context determines the ground-truth relation and the RE models should be able to correctly identify the relations reflected by the textual context.
HACMan: Learning Hybrid Actor-Critic Maps for 6D Non-Prehensile Manipulation
In this work, we introduce Hybrid Actor-Critic Maps for Manipulation (HACMan), a reinforcement learning approach for 6D non-prehensile manipulation of objects using point cloud observations.
Context-faithful Prompting for Large Language Models
However, their reliance on parametric knowledge may cause them to overlook contextual cues, leading to incorrect predictions in context-sensitive NLP tasks (e. g., knowledge acquisition tasks).
Multi-hop Evidence Retrieval for Cross-document Relation Extraction
Relation Extraction (RE) has been extended to cross-document scenarios because many relations are not simply described in a single document.
Continual Contrastive Finetuning Improves Low-Resource Relation Extraction
In this paper, we aim at bridging the gap and propose to pretrain and finetune the RE model using consistent objectives of contrastive learning.
On-the-fly Denoising for Data Augmentation in Natural Language Understanding
However, data augmentation may introduce noisy data that impairs training.
Parameter-Efficient Tuning with Special Token Adaptation
Parameter-efficient tuning aims at updating only a small subset of parameters when adapting a pretrained model to downstream tasks.
Summarization as Indirect Supervision for Relation Extraction
Considering that summarization tasks aim at acquiring concise expressions of synoptical information from the longer context, these tasks naturally align with the objective of RE, i. e., extracting a kind of synoptical information that describes the relation of entity mentions.
Ranked #6 on
Relation Extraction
on TACRED
Should We Rely on Entity Mentions for Relation Extraction? Debiasing Relation Extraction with Counterfactual Analysis
In this paper, we propose the CORE (Counterfactual Analysis based Relation Extraction) debiasing method that guides the RE models to focus on the main effects of textual context without losing the entity information.
GRAPHCACHE: Message Passing as Caching for Sentence-Level Relation Extraction
GRAPHCACHE aggregates the features from sentences in the whole dataset to learn global representations of properties, and use them to augment the local features within individual sentences.
Answer Consolidation: Formulation and Benchmarking
Current question answering (QA) systems primarily consider the single-answer scenario, where each question is assumed to be paired with one correct answer.
Forgetting and Imbalance in Robot Lifelong Learning with Off-policy Data
We propose the Offline Distillation Pipeline to break this trade-off by separating the training procedure into an online interaction phase and an offline distillation phase. Second, we find that training with the imbalanced off-policy data from multiple environments across the lifetime creates a significant performance drop.
Sharpness-Aware Minimization with Dynamic Reweighting
Deep neural networks are often overparameterized and may not easily achieve model generalization.
Prix-LM: Pretraining for Multilingual Knowledge Base Construction
To achieve this, it is crucial to represent multilingual knowledge in a shared/unified space.
Contrastive Out-of-Distribution Detection for Pretrained Transformers
Pretrained Transformers achieve remarkable performance when training and test data are from the same distribution.
Learning from Noisy Labels for Entity-Centric Information Extraction
Recent information extraction approaches have relied on training deep neural models.
Ranked #1 on
Named Entity Recognition (NER)
on CoNLL++
Lyapunov Barrier Policy Optimization
Current RL agents explore the environment without considering these constraints, which can lead to damage to the hardware or even other agents in the environment.
An Improved Baseline for Sentence-level Relation Extraction
Sentence-level relation extraction (RE) aims at identifying the relationship between two entities in a sentence.
Ranked #2 on
Relation Extraction
on Re-TACRED
PLAS: Latent Action Space for Offline Reinforcement Learning
The goal of offline reinforcement learning is to learn a policy from a fixed dataset, without further interactions with the environment.
Document-Level Relation Extraction with Adaptive Thresholding and Localized Context Pooling
In this paper, we propose two novel techniques, adaptive thresholding and localized context pooling, to solve the multi-label and multi-entity problems.
Ranked #6 on
Relation Extraction
on ReDocRED
Document-level Relation Extraction
Multi-Label Classification
+2
Learning Off-Policy with Online Planning
In this work, we investigate a novel instantiation of H-step lookahead with a learned model and a terminal value function learned by a model-free off-policy algorithm, named Learning Off-Policy with Online Planning (LOOP).
A Variational Approach to Unsupervised Sentiment Analysis
Our objective function is to predict an opinion word given a target word while our ultimate goal is to learn a sentiment classifier.
IsoBN: Fine-Tuning BERT with Isotropic Batch Normalization
Fine-tuning pre-trained language models (PTLMs), such as BERT and its better variant RoBERTa, has been a common practice for advancing performance in natural language understanding (NLU) tasks.
Improving BERT Fine-tuning with Embedding Normalization
Large pre-trained sentence encoders like BERT start a new chapter in natural language processing.
Learning from Explanations with Neural Execution Tree
While deep neural networks have achieved impressive performance on a range of NLP tasks, these data-hungry models heavily rely on labeled data, which restricts their applications in scenarios where data annotation is expensive.
NERO: A Neural Rule Grounding Framework for Label-Efficient Relation Extraction
The soft matching module learns to match rules with semantically similar sentences such that raw corpora can be automatically labeled and leveraged by the RE module (in a much better coverage) as augmented supervision, in addition to the exactly matched sentences.
Environment Probing Interaction Policies
A key challenge in reinforcement learning (RL) is environment generalization: a policy trained to solve a task in one environment often fails to solve the same task in a slightly different test environment.
A Variational Approach to Weakly Supervised Document-Level Multi-Aspect Sentiment Classification
These word pairs can be extracted by using dependency parsers and simple rules.
Self-regulation: Employing a Generative Adversarial Network to Improve Event Detection
Due to the ability of encoding and mapping semantic information into a high-dimensional latent feature space, neural networks have been successfully used for detecting events to a certain extent.
Image-Image Search for Comparable Corpora Construction
We present a novel method of comparable corpora construction.
SWEET: Serving the Web by Exploiting Email Tunnels
As the operation of SWEET is not bound to specific email providers we argue that a censor will need to block all email communications in order to disrupt SWEET, which is infeasible as email constitutes an important part of today's Internet.
Cryptography and Security
