Search Results for author:
Found 72 papers, 44 papers with code
Visualizing Cross‐Lingual Discourse Relations in Multilingual TED Corpora
This paper presents an interactive data dashboard that provides users with an overview of the preservation of discourse relations among 28 language pairs.
Modeling Mathematical Notation Semantics in Academic Papers
Natural language models often fall short when understanding and generating mathematical notation.
Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models
Reward-based alignment methods for large language models (LLMs) face two key limitations: vulnerability to reward hacking, where models exploit flaws in the reward signal; and reliance on brittle, labor-intensive prompt engineering when LLMs are used as reward models.
Stealing Creator's Workflow: A Creator-Inspired Agentic Framework with Iterative Feedback Loop for Improved Scientific Short-form Generation
Generating engaging, accurate short-form videos from scientific papers is challenging due to content complexity and the gap between expert authors and readers.
Align to Structure: Aligning Large Language Models with Structural Information
Generating long, coherent text remains a challenge for large language models (LLMs), as they lack hierarchical planning and structured organization in discourse generation.
A Framework for Robust Cognitive Evaluation of LLMs
Emergent cognitive abilities in large language models (LLMs) have been widely observed, but their nature and underlying mechanisms remain poorly understood.
Learning a High-quality Robotic Wiping Policy Using Systematic Reward Analysis and Visual-Language Model Based Curriculum
Autonomous robotic wiping is an important task in various industries, ranging from industrial manufacturing to sanitization in healthcare.
RoSTE: An Efficient Quantization-Aware Supervised Fine-Tuning Approach for Large Language Models
Supervised fine-tuning is a standard method for adapting pre-trained large language models (LLMs) to downstream tasks.
ScholaWrite: A Dataset of End-to-End Scholarly Writing Process
Writing is a cognitively demanding task involving continuous decision-making, heavy use of working memory, and frequent switching between multiple activities.
Anchors Aweigh! Sail for Optimal Unified Multi-Modal Representations
To address these issues, we propose the need for adaptive anchor binding methods, exemplified by our framework CentroBind.
LearnerVoice: A Dataset of Non-Native English Learners' Spontaneous Speech
Our linguistic analysis reveals that transcriptions in our dataset contain L2S (L2 learner's Spontaneous speech) features, consisting of ungrammatical expressions and disfluencies (e. g., filler words, word repetitions, self-repairs, false starts), significantly more than native speech datasets.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Human-AI Collaborative Taxonomy Construction: A Case Study in Profession-Specific Writing Assistants
Large Language Models (LLMs) have assisted humans in several writing tasks, including text revision and story generation.
ISR-DPO: Aligning Large Multimodal Models for Videos by Iterative Self-Retrospective DPO
Iterative self-improvement, a concept extending beyond personal growth, has found powerful applications in machine learning, particularly in transforming weak models into strong ones.
Learning Reward and Policy Jointly from Demonstration and Preference Improves Alignment
Aligning human preference and value is an important requirement for building contemporary foundation models and embodied AI.
On the Sequence Evaluation based on Stochastic Processes
Recent methods that utilize stochastic processes to capture the intrinsic dynamics of sequences have shown superior performance in generative modeling.
Confidence Calibration and Rationalization for LLMs via Multi-Agent Deliberation
Uncertainty estimation is a significant issue for current large language models (LLMs) that are generally poorly calibrated and over-confident, especially with reinforcement learning from human feedback (RLHF).
Dynamic Multi-Reward Weighting for Multi-Style Controllable Generation
Textual style expresses a diverse set of information, including interpersonal dynamics (e. g., formality) and the author's emotions or attitudes (e. g., disgust).
Shallow Synthesis of Knowledge in GPT-Generated Texts: A Case Study in Automatic Related Work Composition
Numerous AI-assisted scholarly applications have been developed to aid different stages of the research process.
Chain-of-Instructions: Compositional Instruction Tuning on Large Language Models
Fine-tuning large language models (LLMs) with a collection of large and diverse instructions has improved the model's generalization to different tasks, even for unseen tasks.
II-MMR: Identifying and Improving Multi-modal Multi-hop Reasoning in Visual Question Answering
II-MMR then analyzes this path to identify different reasoning cases in current VQA benchmarks by estimating how many hops and what types (i. e., visual or beyond-visual) of reasoning are required to answer the question.
Threads of Subtlety: Detecting Machine-Generated Texts Through Discourse Motifs
With the advent of large language models (LLM), the line between human-crafted and machine-generated texts has become increasingly blurred.
Tuning Large Multimodal Models for Videos using Reinforcement Learning from AI Feedback
Recent advancements in large language models have influenced the development of video large multimodal models (VLMMs).
SelectLLM: Can LLMs Select Important Instructions to Annotate?
However, how to select unlabelled instructions is not well-explored, especially in the context of LLMs.
Under the Surface: Tracking the Artifactuality of LLM-Generated Data
This work delves into the expanding role of large language models (LLMs) in generating artificial data.
BBScore: A Brownian Bridge Based Metric for Assessing Text Coherence
In summary, we present a novel Brownian bridge coherence metric capable of measuring both local and global text coherence, while circumventing the need for end-to-end model training.
Which Modality should I use -- Text, Motif, or Image? : Understanding Graphs with Large Language Models
Our research integrates graph data with Large Language Models (LLMs), which, despite their advancements in various fields using large text corpora, face limitations in encoding entire graphs due to context size constraints.
Dialogue Chain-of-Thought Distillation for Commonsense-aware Conversational Agents
Hence, our focus is to facilitate such multi-hop reasoning over a dialogue context, namely dialogue chain-of-thought (CoT) reasoning.
Benchmarking Cognitive Biases in Large Language Models as Evaluators
We then evaluate the quality of ranking outputs introducing the Cognitive Bias Benchmark for LLMs as Evaluators (CoBBLEr), a benchmark to measure six different cognitive biases in LLM evaluation outputs, such as the Egocentric bias where a model prefers to rank its own outputs highly in evaluation.
Story Visualization by Online Text Augmentation with Context Memory
Story visualization (SV) is a challenging text-to-image generation task for the difficulty of not only rendering visual details from the text descriptions but also encoding a long-term context across multiple sentences.
Ranked #3 on
Story Visualization
on Pororo
Prefer to Classify: Improving Text Classifiers via Auxiliary Preference Learning
In this paper, we investigate task-specific preferences between pairs of input texts as a new alternative way for such auxiliary data annotation.
An Analysis of Reader Engagement in Literary Fiction through Eye Tracking and Linguistic Features
Capturing readers' engagement in fiction is a challenging but important aspect of narrative understanding.
infoVerse: A Universal Framework for Dataset Characterization with Multidimensional Meta-information
However, not all samples in these datasets are equally valuable for learning, as some may be redundant or noisy.
Annotation Imputation to Individualize Predictions: Initial Studies on Distribution Dynamics and Model Predictions
In our analysis of the results, we found that the choice of imputation method significantly impacts soft label changes and distribution.
A Survey of Diffusion Models in Natural Language Processing
In NLP, diffusion models have been used in a variety of applications, such as natural language generation, sentiment analysis, topic modeling, and machine translation.
Complex Mathematical Symbol Definition Structures: A Dataset and Model for Coordination Resolution in Definition Extraction
We also introduce a new definition extraction method that masks mathematical symbols, creates a copy of each sentence for each symbol, specifies a target symbol, and predicts its corresponding definition spans using slot filling.
"Is the Pope Catholic?" Applying Chain-of-Thought Reasoning to Understanding Conversational Implicatures
Conversational implicatures are pragmatic inferences that require listeners to deduce the intended meaning conveyed by a speaker from their explicit utterances.
CoEdIT: Text Editing by Task-Specific Instruction Tuning
We present a large language model fine-tuned on a diverse collection of task-specific instructions for text editing (a total of 82K instructions).
Decoding the End-to-end Writing Trajectory in Scholarly Manuscripts
We also provide ManuScript, an original dataset annotated with a simplified version of our taxonomy to show writer actions and the intentions behind them.
The Semantic Reader Project: Augmenting Scholarly Documents through AI-Powered Interactive Reading Interfaces
Scholarly publications are key to the transfer of knowledge from scholars to others.
Cluster-Guided Label Generation in Extreme Multi-Label Classification
For extreme multi-label classification (XMC), existing classification-based models poorly perform for tail labels and often ignore the semantic relations among labels, like treating "Wikipedia" and "Wiki" as independent and separate labels.
Everyone's Voice Matters: Quantifying Annotation Disagreement Using Demographic Information
Particularly, we extract disagreement labels from the annotators' voting histories in the five subjective datasets, and then fine-tune language models to predict annotators' disagreement.
Quirk or Palmer: A Comparative Study of Modal Verb Frameworks with Annotated Datasets
We observe that both frameworks have similar inter-annotator agreements, despite having different numbers of sense types (8 for Quirk and 3 for Palmer).
A Comparative Study on Textual Saliency of Styles from Eye Tracking, Annotations, and Language Models
We develop a variety of methods to derive style saliency scores over text using the collected eye dataset.
Improving Iterative Text Revision by Learning Where to Edit from Other Revision Tasks
Leveraging datasets from other related text editing NLP tasks, combined with the specification of editable spans, leads our system to more accurately model the process of iterative text refinement, as evidenced by empirical results and human evaluations.
RedPen: Region- and Reason-Annotated Dataset of Unnatural Speech
We present a novel speech dataset, RedPen, with human annotations on unnatural speech regions and their corresponding reasons.
StyLEx: Explaining Style Using Human Lexical Annotations
Large pre-trained language models have achieved impressive results on various style classification tasks, but they often learn spurious domain-specific words to make predictions (Hayati et al., 2021).
Rethinking Annotation: Can Language Learners Contribute?
Researchers have traditionally recruited native speakers to provide annotations for widely used benchmark datasets.
Read, Revise, Repeat: A System Demonstration for Human-in-the-loop Iterative Text Revision
Examining and evaluating the capability of large language models for making continuous revisions and collaborating with human writers is a critical step towards building effective writing assistants.
Understanding Iterative Revision from Human-Written Text
Writing is, by nature, a strategic, adaptive, and more importantly, an iterative process.
Understanding Out-of-distribution: A Perspective of Data Dynamics
Despite machine learning models' success in Natural Language Processing (NLP) tasks, predictions from these models frequently fail on out-of-distribution (OOD) samples.
What Makes Better Augmentation Strategies? Augment Difficult but Not too Different
Remarkably, our method is more effective on the challenging low-data and class-imbalanced regimes, and the learned augmentation policy is well-transferable to the different tasks and models.
Does BERT Learn as Humans Perceive? Understanding Linguistic Styles through Lexica
People convey their intention and attitude through linguistic styles of the text that they write.
Zero-shot Natural Language Video Localization
Understanding videos to localize moments with natural language often requires large expensive annotated video regions paired with language queries.
Style is NOT a single variable: Case Studies for Cross-Stylistic Language Understanding
This paper provides the benchmark corpus (XSLUE) that combines existing datasets and collects a new one for sentence-level cross-style language understanding and evaluation.
Plan ahead: Self-Supervised Text Planning for Paragraph Completion Task
To address that, we propose a self-supervised text planner SSPlanner that predicts what to say first (content prediction), then guides the pretrained language model (surface realization) using the predicted content.
Document-Level Definition Detection in Scholarly Documents: Existing Models, Error Analyses, and Future Directions
Based on this analysis, we develop a new definition detection system, HEDDEx, that utilizes syntactic features, transformer encoders, and heuristic filters, and evaluate it on a standard sentence-level benchmark.
GenAug: Data Augmentation for Finetuning Text Generators
We also examine the relationship between the amount of augmentation and the quality of the generated text.
Augmenting Scientific Papers with Just-in-Time, Position-Sensitive Definitions of Terms and Symbols
We introduce ScholarPhi, an augmented reading interface with four novel features: (1) tooltips that surface position-sensitive definitions from elsewhere in a paper, (2) a filter over the paper that "declutters" it to reveal how the term or symbol is used across the paper, (3) automatic equation diagrams that expose multiple definitions in parallel, and (4) an automatically generated glossary of important terms and symbols.
INSPIRED: Toward Sociable Recommendation Dialog Systems
To better understand how humans make recommendations in communication, we design an annotation scheme related to recommendation strategies based on social science theories and annotate these dialogs.
Posterior Calibrated Training on Sentence Classification Tasks
Here we propose an end-to-end training procedure called posterior calibrated (PosCal) training that directly optimizes the objective while minimizing the difference between the predicted and empirical posterior probabilities. We show that PosCal not only helps reduce the calibration error but also improve task performance by penalizing drops in performance of both objectives.
Style is NOT a single variable: Case Studies for Cross-Style Language Understanding
This paper provides the benchmark corpus (xSLUE) that combines existing datasets and collects a new one for sentence-level cross-style language understanding and evaluation.
Recommendation as a Communication Game: Self-Supervised Bot-Play for Goal-oriented Dialogue
These issues can be alleviated by treating recommendation as an interactive dialogue task instead, where an expert recommender can sequentially ask about someone's preferences, react to their requests, and recommend more appropriate items.
(Male, Bachelor) and (Female, Ph.D) have different connotations: Parallelly Annotated Stylistic Language Dataset with Multiple Personas
Stylistic variation in text needs to be studied with different aspects including the writer's personal traits, interpersonal relations, rhetoric, and more.
Linguistic Versus Latent Relations for Modeling Coherent Flow in Paragraphs
In order to produce a coherent flow of text, we explore two forms of intersentential relations in a paragraph: one is a human-created linguistical relation that forms a structure (e. g., discourse tree) and the other is a relation from latent representation learned from the sentences themselves.
Bridging Knowledge Gaps in Neural Entailment via Symbolic Models
We focus on filling these knowledge gaps in the Science Entailment task, by leveraging an external structured knowledge base (KB) of science facts.
AdvEntuRe: Adversarial Training for Textual Entailment with Knowledge-Guided Examples
We consider the problem of learning textual entailment models with limited supervision (5K-10K training examples), and present two complementary approaches for it.
A Dataset of Peer Reviews (PeerRead): Collection, Insights and NLP Applications
In the first task, we show that simple models can predict whether a paper is accepted with up to 21% error reduction compared to the majority baseline.
Actionable Email Intent Modeling with Reparametrized RNNs
Emails in the workplace are often intentional calls to action for its recipients.
Detecting and Explaining Causes From Text For a Time Series Event
Our quantitative and human analysis show empirical evidence that our method successfully extracts meaningful causality relationships between time series with textual features and generates appropriate explanation between them.
