Diffusion of Thoughts: Chain-of-Thought Reasoning in Diffusion Language Models
Diffusion models have gained attention in text processing, offering many potential advantages over traditional autoregressive models. This work explores the integration of diffusion models and...
View ArticleAsking Multimodal Clarifying Questions in Mixed-Initiative Conversational Search
In mixed-initiative conversational search systems, clarifying questions are used to help users who struggle to express their intentions in a single query. These questions aim to uncover user's...
View ArticleUnsupervised Sign Language Translation and Generation
Motivated by the success of unsupervised neural machine translation (UNMT), we introduce an unsupervised sign language translation and generation network (USLNet), which learns from abundant...
View ArticleOrderBkd: Textual backdoor attack through repositioning
The use of third-party datasets and pre-trained machine learning models poses a threat to NLP systems due to possibility of hidden backdoor attacks. Existing attacks involve poisoning the data samples...
View ArticleAuxiliary Tasks to Boost Biaffine Semantic Dependency Parsing
The biaffine parser of Dozat and Manning (2017) was successfully extended to semantic dependency parsing (SDP) (Dozat and Manning, 2018). Its performance on graphs is surprisingly high given that,...
View ArticleLarge Language Models "Ad Referendum": How Good Are They at Machine...
This study evaluates the machine translation (MT) quality of two state-of-the-art large language models (LLMs) against a tradition-al neural machine translation (NMT) system across four language pairs...
View ArticleThe Sound of Healthcare: Improving Medical Transcription ASR Accuracy with...
In the rapidly evolving landscape of medical documentation, transcribing clinical dialogues accurately is increasingly paramount. This study explores the potential of Large Language Models (LLMs) to...
View ArticleDetecting the Clinical Features of Difficult-to-Treat Depression using...
Difficult-to-treat depression (DTD) has been proposed as a broader and more clinically comprehensive perspective on a person's depressive disorder where despite treatment, they continue to experience...
View ArticleAutoMathText: Autonomous Data Selection with Language Models for Mathematical...
To improve language models' proficiency in mathematical reasoning via continual pretraining, we introduce a novel strategy that leverages base language models for autonomous data selection. Departing...
View ArticleAnchor-based Large Language Models
Large language models (LLMs) predominantly employ decoder-only transformer architectures, necessitating the retention of keys/values information for historical tokens to provide contextual information...
View ArticleStep-On-Feet Tuning: Scaling Self-Alignment of LLMs via Bootstrapping
Self-alignment is an effective way to reduce the cost of human annotation while ensuring promising model capability. However, most current methods complete the data collection and training steps in a...
View ArticleTopic Modeling as Multi-Objective Contrastive Optimization
Recent representation learning approaches enhance neural topic models by optimizing the weighted linear combination of the evidence lower bound (ELBO) of the log-likelihood and the contrastive learning...
View ArticleShow Me How It's Done: The Role of Explanations in Fine-Tuning Language Models
Our research demonstrates the significant benefits of using fine-tuning with explanations to enhance the performance of language models. Unlike prompting, which maintains the model's parameters,...
View ArticleMAFIA: Multi-Adapter Fused Inclusive LanguAge Models
Pretrained Language Models (PLMs) are widely used in NLP for various tasks. Recent studies have identified various biases that such models exhibit and have proposed methods to correct these biases....
View ArticleThe Balancing Act: Unmasking and Alleviating ASR Biases in Portuguese
In the field of spoken language understanding, systems like Whisper and Multilingual Massive Speech (MMS) have shown state-of-the-art performances. This study is dedicated to a comprehensive...
View ArticlePushing The Limit of LLM Capacity for Text Classification
The value of text classification's future research has encountered challenges and uncertainties, due to the extraordinary efficacy demonstrated by large language models (LLMs) across numerous...
View ArticleAraSpider: Democratizing Arabic-to-SQL
This study presents AraSpider, the first Arabic version of the Spider dataset, aimed at improving natural language processing (NLP) in the Arabic-speaking community. Four multilingual translation...
View ArticleQuality Does Matter: A Detailed Look at the Quality and Utility of Web-Mined...
We conducted a detailed analysis on the quality of web-mined corpora for two low-resource languages (making three language pairs, English-Sinhala, English-Tamil and Sinhala-Tamil). We ranked each...
View ArticleIntrinsic Task-based Evaluation for Referring Expression Generation
Recently, a human evaluation study of Referring Expression Generation (REG) models had an unexpected conclusion: on \textsc{webnlg}, Referring Expressions (REs) generated by the state-of-the-art neural...
View ArticleSALAD: Smart AI Language Assistant Daily
SALAD is an AI-driven language-learning application designed to help foreigners learn Japanese. It offers translations in Kanji-Kana-Romaji, speech recognition, translated audio, vocabulary tracking,...
View ArticleD\'olares or Dollars? Unraveling the Bilingual Prowess of Financial LLMs...
Despite Spanish's pivotal role in the global finance industry, a pronounced gap exists in Spanish financial natural language processing (NLP) and application studies compared to English, especially in...
View ArticleCan LLMs Produce Faithful Explanations For Fact-checking? Towards Faithful...
Fact-checking research has extensively explored verification but less so the generation of natural-language explanations, crucial for user trust. While Large Language Models (LLMs) excel in text...
View ArticleChain-of-Layer: Iteratively Prompting Large Language Models for Taxonomy...
Automatic taxonomy induction is crucial for web search, recommendation systems, and question answering. Manual curation of taxonomies is expensive in terms of human effort, making automatic taxonomy...
View ArticleHow do Large Language Models Navigate Conflicts between Honesty and Helpfulness?
In day-to-day communication, people often approximate the truth - for example, rounding the time or omitting details - in order to be maximally helpful to the listener. How do large language models...
View ArticlePreviously on the Stories: Recap Snippet Identification for Story Reading
Similar to the "previously-on" scenes in TV shows, recaps can help book reading by recalling the readers' memory about the important elements in previous texts to better understand the ongoing plot....
View ArticleLow-Resource Counterspeech Generation for Indic Languages: The Case of...
With the rise of online abuse, the NLP community has begun investigating the use of neural architectures to generate counterspeech that can "counter" the vicious tone of such abusive speech and...
View ArticleAmerican Sign Language Video to Text Translation
Sign language to text is a crucial technology that can break down communication barriers for individuals with hearing difficulties. We replicate and try to improve on a recently published study. We...
View ArticleTransGPT: Multi-modal Generative Pre-trained Transformer for Transportation
Natural language processing (NLP) is a key component of intelligent transportation systems (ITS), but it faces many challenges in the transportation domain, such as domain-specific knowledge and data,...
View ArticleThrough the Lens of Split Vote: Exploring Disagreement, Difficulty and...
In legal decisions, split votes (SV) occur when judges cannot reach a unanimous decision, posing a difficulty for lawyers who must navigate diverse legal arguments and opinions. In high-stakes domains,...
View ArticlePrompt Perturbation in Retrieval-Augmented Generation based Large Language...
The robustness of large language models (LLMs) becomes increasingly important as their use rapidly grows in a wide range of domains. Retrieval-Augmented Generation (RAG) is considered as a means to...
View ArticleNatural Language Reinforcement Learning
Reinforcement Learning (RL) has shown remarkable abilities in learning policies for decision-making tasks. However, RL is often hindered by issues such as low sample efficiency, lack of...
View ArticleGeneralizing Conversational Dense Retrieval via LLM-Cognition Data Augmentation
Conversational search utilizes muli-turn natural language contexts to retrieve relevant passages. Existing conversational dense retrieval models mostly view a conversation as a fixed sequence of...
View ArticleUsing Large Language Models for Student-Code Guided Test Case Generation in...
In computer science education, test cases are an integral part of programming assignments since they can be used as assessment items to test students' programming knowledge and provide personalized...
View ArticleSemi-Supervised Learning for Bilingual Lexicon Induction
We consider the problem of aligning two sets of continuous word representations, corresponding to languages, to a common space in order to infer a bilingual lexicon. It was recently shown that it is...
View ArticleGemini Goes to Med School: Exploring the Capabilities of Multimodal Large...
Large language models have the potential to be valuable in the healthcare industry, but it's crucial to verify their safety and effectiveness through rigorous evaluation. For this purpose, we...
View ArticleEvent-Keyed Summarization
We introduce event-keyed summarization (EKS), a novel task that marries traditional summarization and document-level event extraction, with the goal of generating a contextualized summary for a...
View ArticleInstruct Once, Chat Consistently in Multiple Rounds: An Efficient Tuning...
Tuning pretrained language models for dialogue generation has been a prevalent paradigm for building capable dialogue agents. Yet, traditional tuning narrowly views dialogue generation as resembling...
View ArticleNLP for Knowledge Discovery and Information Extraction from Energetics Corpora
We present a demonstration of the utility of NLP for aiding research into energetic materials and associated systems. The NLP method enables machine understanding of textual data, offering an automated...
View ArticleSpeechCLIP+: Self-supervised multi-task representation learning for speech...
The recently proposed visually grounded speech model SpeechCLIP is an innovative framework that bridges speech and text through images via CLIP without relying on text transcription. On this basis,...
View ArticleShould I try multiple optimizers when fine-tuning pre-trained Transformers...
NLP research has explored different neural model architectures and sizes, datasets, training objectives, and transfer learning techniques. However, the choice of optimizer during training has not been...
View ArticleLiFi: Lightweight Controlled Text Generation with Fine-Grained Control Codes
In the rapidly evolving field of text generation, the demand for more precise control mechanisms has become increasingly apparent. To address this need, we present a novel methodology, LIFI, which...
View ArticleA Thorough Examination of Decoding Methods in the Era of LLMs
Decoding methods play an indispensable role in converting language models from next-token predictors into practical task solvers. Prior research on decoding methods, primarily focusing on task-specific...
View ArticleTL;DR Progress: Multi-faceted Literature Exploration in Text Summarization
This paper presents TL;DR Progress, a new tool for exploring the literature on neural text summarization. It organizes 514~papers based on a comprehensive annotation scheme for text summarization...
View ArticleInvestigating Consistency in Query-Based Meeting Summarization: A Comparative...
With more and more advanced data analysis techniques emerging, people will expect these techniques to be applied in more complex tasks and solve problems in our daily lives. Text Summarization is one...
View ArticleCan LLMs Recognize Toxicity? Structured Toxicity Investigation Framework and...
In the pursuit of developing Large Language Models (LLMs) that adhere to societal standards, it is imperative to discern the existence of toxicity in the generated text. The majority of existing...
View ArticleGenTranslate: Large Language Models are Generative Multilingual Speech and...
Recent advances in large language models (LLMs) have stepped forward the development of multilingual speech and machine translation by its reduced representation errors and incorporated external...
View ArticleHistory, Development, and Principles of Large Language Models-An Introductory...
Language models serve as a cornerstone in natural language processing (NLP), utilizing mathematical methods to generalize language laws and knowledge for prediction and generation. Over extensive...
View ArticleEvaluation Metrics for Text Data Augmentation in NLP
Recent surveys on data augmentation for natural language processing have reported different techniques and advancements in the field. Several frameworks, tools, and repositories promote the...
View ArticleEntGPT: Linking Generative Large Language Models with Knowledge Bases
The ability of Large Language Models (LLMs) to generate factually correct output remains relatively unexplored due to the lack of fact-checking and knowledge grounding during training and inference. In...
View ArticleNICE: To Optimize In-Context Examples or Not?
Recent works have shown that large language models (LLMs) work remarkably well on a wide range of tasks through in-context learning and optimization of in-context examples (ICE). However, most of these...
View Article
