Search Results for author:
Found 31 papers, 21 papers with code
To Code, or Not To Code? Exploring Impact of Code in Pre-training
In this work, we systematically investigate the impact of code data on general performance.
500xCompressor: Generalized Prompt Compression for Large Language Models
Prompt compression is crucial for enhancing inference speed, reducing costs, and improving user experience.
Replacing Judges with Juries: Evaluating LLM Generations with a Panel of Diverse Models
As Large Language Models (LLMs) have become more advanced, they have outpaced our abilities to accurately evaluate their quality.
StarCoder 2 and The Stack v2: The Next Generation
Our large model, StarCoder2- 15B, significantly outperforms other models of comparable size.
Ranked #27 on
Code Generation
on MBPP
Unlocking Structure Measuring: Introducing PDD, an Automatic Metric for Positional Discourse Coherence
Recent large language models (LLMs) have shown remarkable performance in aligning generated text with user intentions across various tasks.
Instruct-SCTG: Guiding Sequential Controlled Text Generation through Instructions
Instruction-tuned large language models have shown remarkable performance in aligning generated text with user intentions across various tasks.
Specialist or Generalist? Instruction Tuning for Specific NLP Tasks
Although instruction tuning has proven to be a data-efficient method for transforming LLMs into such generalist models, their performance still lags behind specialist models trained exclusively for specific tasks.
Sparkles: Unlocking Chats Across Multiple Images for Multimodal Instruction-Following Models
Furthermore, we construct SparklesEval, a GPT-assisted benchmark for quantitatively assessing a model's conversational competence across multiple images and dialogue turns.
PandaGPT: One Model To Instruction-Follow Them All
To do so, PandaGPT combines the multimodal encoders from ImageBind and the large language models from Vicuna.
Biomedical Named Entity Recognition via Dictionary-based Synonym Generalization
To alleviate the need of human effort, dictionary-based approaches have been proposed to extract named entities simply based on a given dictionary.
COFFEE: A Contrastive Oracle-Free Framework for Event Extraction
In this study, we consider a more realistic setting of this task, namely the Oracle-Free Event Extraction (OFEE) task, where only the input context is given without any oracle information, including event type, event ontology and trigger word.
Plug-and-Play Recipe Generation with Content Planning
Specifically, it optimizes the joint distribution of the natural language sequence and the global content plan in a plug-and-play manner.
Momentum Decoding: Open-ended Text Generation As Graph Exploration
In this study, we formulate open-ended text generation from a new perspective, i. e., we view it as an exploration process within a directed graph.
An Empirical Study On Contrastive Search And Contrastive Decoding For Open-ended Text Generation
In the study, we empirically compare the two recently proposed decoding methods, i. e. Contrastive Search (CS) and Contrastive Decoding (CD), for open-ended text generation.
Contrastive Search Is What You Need For Neural Text Generation
Based on our findings, we further assess the contrastive search decoding method using off-the-shelf LMs on four generation tasks across 16 languages.
From Easy to Hard: A Dual Curriculum Learning Framework for Context-Aware Document Ranking
In this work, we propose a curriculum learning framework for context-aware document ranking, in which the ranking model learns matching signals between the search context and the candidate document in an easy-to-hard manner.
Language Models Can See: Plugging Visual Controls in Text Generation
MAGIC is a flexible framework and is theoretically compatible with any text generation tasks that incorporate image grounding.
A Contrastive Framework for Neural Text Generation
Text generation is of great importance to many natural language processing applications.
Measuring and Reducing Model Update Regression in Structured Prediction for NLP
First, we measure and analyze model update regression in different model update settings.
A Survey on Retrieval-Augmented Text Generation
Recently, retrieval-augmented text generation attracted increasing attention of the computational linguistics community.
TaCL: Improving BERT Pre-training with Token-aware Contrastive Learning
Masked language models (MLMs) such as BERT and RoBERTa have revolutionized the field of Natural Language Understanding in the past few years.
Rewire-then-Probe: A Contrastive Recipe for Probing Biomedical Knowledge of Pre-trained Language Models
To catalyse the research in this direction, we release a well-curated biomedical knowledge probing benchmark, MedLAMA, which is constructed based on the Unified Medical Language System (UMLS) Metathesaurus.
Exploring Dense Retrieval for Dialogue Response Selection
In this study, we present a solution to directly select proper responses from a large corpus or even a nonparallel corpus that only consists of unpaired sentences, using a dense retrieval model.
Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue System
Pre-trained language models have been recently shown to benefit task-oriented dialogue (TOD) systems.
Plan-then-Generate: Controlled Data-to-Text Generation via Planning
However, the lack of ability of neural models to control the structure of generated output can be limiting in certain real-world applications.
Few-Shot Table-to-Text Generation with Prototype Memory
Neural table-to-text generation models have achieved remarkable progress on an array of tasks.
Non-Autoregressive Text Generation with Pre-trained Language Models
In this work, we show that BERT can be employed as the backbone of a NAG model to greatly improve performance.
Dialogue Response Selection with Hierarchical Curriculum Learning
As for IC, it progressively strengthens the model's ability in identifying the mismatching information between the dialogue context and a response candidate.
Ranked #3 on
Conversational Response Selection
on RRS
Prototype-to-Style: Dialogue Generation with Style-Aware Editing on Retrieval Memory
A stylistic response generator then takes the prototype and the desired language style as model input to obtain a high-quality and stylistic response.
Stylistic Dialogue Generation via Information-Guided Reinforcement Learning Strategy
To enable better balance between the content quality and the style, we introduce a new training strategy, know as Information-Guided Reinforcement Learning (IG-RL).
