243 citations · 438 across the 54 of their papers we have counts for
30 papers · 1 filter
SSR: Socratic Self-Refine for Large Language Model Reasoning
Haizhou Shi, Ye Liu, Bo Pang +6
Large Language Models (LLMs) have demonstrated remarkable reasoning abilities, yet existing test-time frameworks often rely on coarse self-verification and self-correction, limitin…
Retrofitting Small Multilingual Models for Retrieval: Matching 7B Performance with 300M Parameters
Lifu Tu, Yingbo Zhou, Semih Yavuz
Training effective multilingual embedding models presents unique challenges due to the diversity of languages and task objectives. Although small multilingual models (<1 B paramete…
xGen-small Technical Report
Erik Nijkamp, Bo Pang, Egor Pakhomov +5
We introduce xGen-small, a family of 4B and 9B Transformer decoder models optimized for long-context applications. Our vertically integrated pipeline unites domain-balanced, freque…
BOLT: Bootstrap Long Chain-of-Thought in Language Models without Distillation
Bo Pang, Hanze Dong, Jiacheng Xu +3
Large language models (LLMs), such as o1 from OpenAI, have demonstrated remarkable reasoning capabilities. o1 generates a long chain-of-thought (LongCoT) before answering a questio…
StructTest: Benchmarking LLMs' Reasoning through Compositional Structured Outputs
Hailin Chen, Fangkai Jiao, Mathieu Ravaut +8
The rapid advancement of large language models (LLMs) demands robust, unbiased, and scalable evaluation methods. However, human annotations are costly to scale, model-based evaluat…
CodeTree: Agent-guided Tree Search for Code Generation with Large Language Models
Jierui Li, Hung Le, Yingbo Zhou +3
Pre-trained on massive amounts of code and text data, large language models (LLMs) have demonstrated remarkable achievements in performing code generation tasks. With additional ex…
Investigating Factuality in Long-Form Text Generation: The Roles of Self-Known and Self-Unknown
Lifu Tu, Rui Meng, Shafiq Joty +2
Large language models (LLMs) have demonstrated strong capabilities in text understanding and generation. However, they often lack factuality, producing a mixture of true and false…
JudgeRank: Leveraging Large Language Models for Reasoning-Intensive Reranking
Tong Niu, Shafiq Joty, Ye Liu +3
Accurate document retrieval is crucial for the success of retrieval-augmented generation (RAG) applications, including open-domain question answering and code completion. While lar…
Traffic Light or Light Traffic? Investigating Phrasal Semantics in Large Language Models
Rui Meng, Ye Liu, Lifu Tu +3
Phrases are fundamental linguistic units through which humans convey semantics. This study critically examines the capacity of API-based large language models (LLMs) to comprehend…
Parameter-Efficient Detoxification with Contrastive Decoding
Tong Niu, Caiming Xiong, Semih Yavuz +1
The field of natural language generation has witnessed significant advancements in recent years, including the development of controllable text generation techniques. However, cont…
Unlocking Anticipatory Text Generation: A Constrained Approach for Large Language Models Decoding
Lifu Tu, Semih Yavuz, Jin Qu +4
Large Language Models (LLMs) have demonstrated a powerful ability for text generation. However, achieving optimal results with a given prompt or instruction can be challenging, esp…
DIVKNOWQA: Assessing the Reasoning Ability of LLMs via Open-Domain Question Answering over Knowledge Base and Text
Wenting Zhao, Ye Liu, Tong Niu +5
Large Language Models (LLMs) have exhibited impressive generation capabilities, but they suffer from hallucinations when solely relying on their internal knowledge, especially when…
Investigating Answerability of LLMs for Long-Form Question Answering
Meghana Moorthy Bhat, Rui Meng, Ye Liu +2
As we embark on a new era of LLMs, it becomes increasingly crucial to understand their capabilities, limitations, and differences. Toward making further progress in this direction,…
Few-shot Unified Question Answering: Tuning Models or Prompts?
Srijan Bansal, Semih Yavuz, Bo Pang +2
Question-answering (QA) tasks often investigate specific question types, knowledge domains, or reasoning skills, leading to specialized models catering to specific categories of QA…
HPE:Answering Complex Questions over Text by Hybrid Question Parsing and Execution
Ye Liu, Semih Yavuz, Rui Meng +3
The dominant paradigm of textual question answering systems is based on end-to-end neural networks, which excels at answering natural language questions but falls short on complex…
Efficiently Aligned Cross-Lingual Transfer Learning for Conversational Tasks using Prompt-Tuning
Lifu Tu, Jin Qu, Semih Yavuz +4
Cross-lingual transfer of language models trained on high-resource languages like English has been widely studied for many NLP tasks, but focus on conversational tasks has been rat…
AugTriever: Unsupervised Dense Retrieval and Domain Adaptation by Scalable Data Augmentation
Rui Meng, Ye Liu, Semih Yavuz +6
Dense retrievers have made significant strides in text retrieval and open-domain question answering. However, most of these achievements have relied heavily on extensive human-anno…
Best- Search Algorithm for Neural Text Generation
Jiacheng Xu, Caiming Xiong, Silvio Savarese +1
Modern natural language generation paradigms require a good decoding strategy to obtain quality sequences out of the model. Beam search yields high-quality but low diversity output…
Uni-Parser: Unified Semantic Parser for Question Answering on Knowledge Base and Database
Ye Liu, Semih Yavuz, Rui Meng +3
Parsing natural language questions into executable logical forms is a useful and interpretable way to perform question answering on structured data such as knowledge bases (KB) or…
Prompt-Tuning Can Be Much Better Than Fine-Tuning on Cross-lingual Understanding With Multilingual Language Models
Lifu Tu, Caiming Xiong, Yingbo Zhou
Pre-trained multilingual language models show significant performance gains for zero-shot cross-lingual model transfer on a wide range of natural language understanding (NLU) tasks…
General-to-Specific Transfer Labeling for Domain Adaptable Keyphrase Generation
Rui Meng, Tong Wang, Xingdi Yuan +2
Training keyphrase generation (KPG) models require a large amount of annotated data, which can be prohibitively expensive and often limited to specific domains. In this study, we f…
Improving the Faithfulness of Abstractive Summarization via Entity Coverage Control
Haopeng Zhang, Semih Yavuz, Wojciech Kryscinski +2
Abstractive summarization systems leveraging pre-training language models have achieved superior results on benchmark datasets. However, such models have been shown to be more pron…
Modeling Multi-hop Question Answering as Single Sequence Prediction
Semih Yavuz, Kazuma Hashimoto, Yingbo Zhou +2
Fusion-in-decoder (Fid) (Izacard and Grave, 2020) is a generative question answering (QA) model that leverages passage retrieval with a pre-trained transformer and pushed the state…
OneAligner: Zero-shot Cross-lingual Transfer with One Rich-Resource Language Pair for Low-Resource Sentence Retrieval
Tong Niu, Kazuma Hashimoto, Yingbo Zhou +1
Aligning parallel sentences in multilingual corpora is essential to curating data for downstream applications such as Machine Translation. In this work, we present OneAligner, an a…