Search Results for author:
Found 48 papers, 36 papers with code
Challenges to Open-Domain Constituency Parsing
Neural constituency parsers have reached practical performance on news-domain benchmarks.
ThinkBench: Dynamic Out-of-Distribution Evaluation for Robust LLM Reasoning
Evaluating large language models (LLMs) poses significant challenges, particularly due to issues of data contamination and the leakage of correct answers.
Selection-p: Self-Supervised Task-Agnostic Prompt Compression for Faithfulness and Transferability
Large Language Models (LLMs) have demonstrated impressive capabilities in a wide range of natural language processing tasks when leveraging in-context learning.
Gated Slot Attention for Efficient Linear-Time Sequence Modeling
Linear attention Transformers and their gated variants, celebrated for enabling parallel training and efficient recurrent inference, still fall short in recall-intensive tasks compared to traditional Transformers and demand significant resources for training from scratch.
Not All Preference Pairs Are Created Equal: A Recipe for Annotation-Efficient Iterative Preference Learning
Iterative preference learning, though yielding superior performances, requires online annotated preference labels.
On the Transformations across Reward Model, Parameter Update, and In-Context Prompt
Despite the general capabilities of pre-trained large language models (LLMs), they still need further adaptation to better serve practical applications.
Spotting AI's Touch: Identifying LLM-Paraphrased Spans in Text
To this end, we propose a novel detection framework, paraphrased text span detection (PTD), aiming to identify paraphrased text spans within a text.
Mitigating Catastrophic Forgetting in Large Language Models with Self-Synthesized Rehearsal
When conducting continual learning based on a publicly-released LLM checkpoint, the availability of the original training data may be non-existent.
GSM-Plus: A Comprehensive Benchmark for Evaluating the Robustness of LLMs as Mathematical Problem Solvers
Large language models (LLMs) have achieved impressive performance across various mathematical reasoning benchmarks.
Ranked #1 on
Math Word Problem Solving
on GSM-Plus
Retrieval is Accurate Generation
To address this, we propose to initialize the training oracles using linguistic heuristics and, more importantly, bootstrap the oracles through iterative self-reinforcement.
Knowledge Verification to Nip Hallucination in the Bud
While large language models (LLMs) have demonstrated exceptional performance across various tasks following human alignment, they may still generate responses that sound plausible but contradict factual knowledge, a phenomenon known as hallucination.
Inferflow: an Efficient and Highly Configurable Inference Engine for Large Language Models
We present Inferflow, an efficient and highly configurable inference engine for large language models (LLMs).
Alleviating Hallucinations of Large Language Models through Induced Hallucinations
Experimental results on both discrimination-based and generation-based hallucination evaluation benchmarks, such as TruthfulQA and \textsc{FActScore}, demonstrate that our proposed ICD methods can effectively enhance the factuality of LLMs across various model sizes and families.
Neuro-Symbolic Integration Brings Causal and Reliable Reasoning Proofs
Two lines of approaches are adopted for complex reasoning with LLMs.
A Systematic Evaluation of GPT-4V's Multimodal Capability for Medical Image Analysis
This work conducts an evaluation of GPT-4V's multimodal capability for medical image analysis, with a focus on three representative tasks of radiology report generation, medical visual question answering, and medical visual grounding.
RobustGEC: Robust Grammatical Error Correction Against Subtle Context Perturbation
In this paper, we introduce RobustGEC, a benchmark designed to evaluate the context robustness of GEC systems.
Non-autoregressive Text Editing with Copy-aware Latent Alignments
In this work, we propose a novel non-autoregressive text editing method to circumvent the above issues, by modeling the edit process with latent CTC alignments.
Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models
While large language models (LLMs) have demonstrated remarkable capabilities across a range of downstream tasks, a significant concern revolves around their propensity to exhibit hallucinations: LLMs occasionally generate content that diverges from the user input, contradicts previously generated context, or misaligns with established world knowledge.
Automated Action Model Acquisition from Narrative Texts
Action models, which take the form of precondition/effect axioms, facilitate causal and motivational connections between actions for AI agents.
Disco-Bench: A Discourse-Aware Evaluation Benchmark for Language Modelling
Modeling discourse -- the linguistic phenomena that go beyond individual sentences, is a fundamental yet challenging aspect of natural language processing (NLP).
Explicit Syntactic Guidance for Neural Text Generation
Most existing text generation models follow the sequence-to-sequence paradigm.
Enhancing Grammatical Error Correction Systems with Explanations
Grammatical error correction systems improve written communication by detecting and correcting language mistakes.
Multi-Task Instruction Tuning of LLaMa for Specific Scenarios: A Preliminary Study on Writing Assistance
Proprietary Large Language Models (LLMs), such as ChatGPT, have garnered significant attention due to their exceptional capabilities in handling a diverse range of tasks.
MAGE: Machine-generated Text Detection in the Wild
In practical scenarios, however, the detector faces texts from various domains or LLMs without knowing their sources.
LogiCoT: Logical Chain-of-Thought Instruction-Tuning
LogiCoT serves as an instruction set for teaching models of logical reasoning and elicits general reasoning skills.
EDeR: A Dataset for Exploring Dependency Relations Between Events
We argue that an important type of relation not explored in NLP or IR research to date is that of an event being an argument - required or optional - of another event.
Cross-domain Generalization for AMR Parsing
Based on our observation, we investigate two approaches to reduce the domain distribution divergence of text and AMR features, respectively.
Multi-Granularity Optimization for Non-Autoregressive Translation
Despite low latency, non-autoregressive machine translation (NAT) suffers severe performance deterioration due to the naive independence assumption.
FactMix: Using a Few Labeled In-domain Examples to Generalize to Cross-domain Named Entity Recognition
Few-shot Named Entity Recognition (NER) is imperative for entity tagging in limited resource domains and thus received proper attention in recent years.
Effidit: Your AI Writing Assistant
In Effidit, we significantly expand the capacities of a writing assistant by providing functions in five categories: text completion, error checking, text polishing, keywords to sentences (K2S), and cloud input methods (cloud IME).
Towards Robust Online Dialogue Response Generation
Although pre-trained sequence-to-sequence models have achieved great success in dialogue response generation, chatbots still suffer from generating inconsistent responses in real-world practice, especially in multi-turn settings.
Do Prompts Solve NLP Tasks Using Natural Language?
Thanks to the advanced improvement of large pre-trained language models, prompt-based fine-tuning is shown to be effective on a variety of downstream tasks.
Solving Aspect Category Sentiment Analysis as a Text Generation Task
Aspect category sentiment analysis has attracted increasing research attention.
Investigating Non-local Features for Neural Constituency Parsing
Besides, our method achieves state-of-the-art BERT-based performance on PTB (95. 92 F1) and strong performance on CTB (92. 31 F1).
Ranked #8 on
Constituency Parsing
on Penn Treebank
Knowledge Enhanced Fine-Tuning for Better Handling Unseen Entities in Dialogue Generation
To deal with this problem, instead of introducing knowledge base as the input, we force the model to learn a better semantic representation by predicting the information in the knowledge base, only based on the input context.
Template-Based Named Entity Recognition Using BART
To address the issue, we propose a template-based method for NER, treating NER as a language model ranking problem in a sequence-to-sequence framework, where original sentences and statement templates filled by candidate named entity span are regarded as the source sequence and the target sequence, respectively.
Uni-Encoder: A Fast and Accurate Response Selection Paradigm for Generation-Based Dialogue Systems
The current state-of-the-art ranking methods mainly use an encoding paradigm called Cross-Encoder, which separately encodes each context-candidate pair and ranks the candidates according to their fitness scores.
Ranked #1 on
Conversational Response Selection
on Persona-Chat
Natural Language Inference in Context -- Investigating Contextual Reasoning over Long Texts
Natural language inference (NLI) is a fundamental NLP task, investigating the entailment relationship between two texts.
Does Chinese BERT Encode Word Structure?
Contextualized representations give significantly improved results for a wide range of NLP tasks.
What Have We Achieved on Text Summarization?
Deep learning has led to significant improvement in text summarization with various methods investigated and improved ROUGE scores reported over the years.
On Commonsense Cues in BERT for Solving Commonsense Tasks
We quantitatively investigate the presence of structural commonsense cues in BERT when solving commonsense tasks, and the importance of such cues for the model prediction.
LogiQA: A Challenge Dataset for Machine Reading Comprehension with Logical Reasoning
Machine reading is a fundamental task for testing the capability of natural language understanding, which is closely related to human cognition in many aspects.
MuTual: A Dataset for Multi-Turn Dialogue Reasoning
Non-task oriented dialogue systems have achieved great success in recent years due to largely accessible conversation data and the development of deep learning techniques.
Evaluating Commonsense in Pre-trained Language Models
However, relatively little work has been done investigating commonsense knowledge contained in contextualized representations, which is crucial for human question answering and reading comprehension.
How Can BERT Help Lexical Semantics Tasks?
Contextualized embeddings such as BERT can serve as strong input representations to NLP tasks, outperforming their static embeddings counterparts such as skip-gram, CBOW and GloVe.
Making the Best Use of Review Summary for Sentiment Analysis
In this paper, we conduct a study to exploit methods for better use of summary information.
Hierarchically-Refined Label Attention Network for Sequence Labeling
CRF has been used as a powerful model for statistical sequence labeling.
Ranked #1 on
Part-Of-Speech Tagging
on UD
