58 citations · 182 across the 22 of their papers we have counts for
23 papers
Nemotron-Cascade: Scaling Cascaded Reinforcement Learning for General-Purpose Reasoning Models
Boxin Wang, Chankyu Lee, Nayeon Lee +9
Building general-purpose reasoning models with reinforcement learning (RL) entails substantial cross-domain heterogeneity, including large variation in inference-time response leng…
Separate the Wheat from the Chaff: Winnowing Down Divergent Views in Retrieval Augmented Generation
Song Wang, Zihan Chen, Peng Wang +5
Retrieval-augmented generation (RAG) enhances large language models (LLMs) by integrating external knowledge sources to address their limitations in accessing up-to-date or special…
Evolutionary Profiles for Protein Fitness Prediction
Jigang Fan, Xiaoran Jiao, Shengdong Lin +5
Predicting the fitness impact of mutations is central to protein engineering but constrained by limited assays relative to the size of sequence space. Protein language models (pLMs…
MM-Embed: Universal Multimodal Retrieval with Multimodal LLMs
Sheng-Chieh Lin, Chankyu Lee, Mohammad Shoeybi +3
State-of-the-art retrieval models typically address a straightforward search scenario, in which retrieval tasks are fixed (e.g., finding a passage to answer a specific question) an…
Synergistic Approach for Simultaneous Optimization of Monolingual, Cross-lingual, and Multilingual Information Retrieval
Adel Elmahdy, Sheng-Chieh Lin, Amin Ahmad
Information retrieval across different languages is an increasingly important challenge in natural language processing. Recent approaches based on multilingual pre-trained language…
LTRL: Boosting Long-tail Recognition via Reflective Learning
Qihao Zhao, Yalun Dai, Shen Lin +3
In real-world scenarios, where knowledge distributions exhibit long-tail. Humans manage to master knowledge uniformly across imbalanced distributions, a feat attributed to their di…
Unifying Multimodal Retrieval via Document Screenshot Embedding
Xueguang Ma, Sheng-Chieh Lin, Minghan Li +2
In the real world, documents are organized in different formats and varied modalities. Traditional retrieval pipelines require tailored document parsing techniques and content extr…
FLAME: Factuality-Aware Alignment for Large Language Models
Sheng-Chieh Lin, Luyu Gao, Barlas Oguz +4
Alignment is a standard procedure to fine-tune pre-trained large language models (LLMs) to follow natural language instructions and serve as helpful AI assistants. We have observed…
Improving Conversational Passage Re-ranking with View Ensemble
Jia-Huei Ju, Sheng-Chieh Lin, Ming-Feng Tsai +1
This paper presents ConvRerank, a conversational passage re-ranker that employs a newly developed pseudo-labeling approach. Our proposed view-ensemble method enhances the quality o…
How to Train Your DRAGON: Diverse Augmentation Towards Generalizable Dense Retrieval
Sheng-Chieh Lin, Akari Asai, Minghan Li +5
Various techniques have been developed in recent years to improve dense retrieval (DR), such as unsupervised contrastive learning and pseudo-query generation. Existing DRs, however…
SLIM: Sparsified Late Interaction for Multi-Vector Retrieval with Inverted Indexes
Minghan Li, Sheng-Chieh Lin, Xueguang Ma +1
This paper introduces Sparsified Late Interaction for Multi-vector (SLIM) retrieval with inverted indexes. Multi-vector retrieval methods have demonstrated their effectiveness on v…
CITADEL: Conditional Token Interaction via Dynamic Lexical Routing for Efficient and Effective Multi-Vector Retrieval
Minghan Li, Sheng-Chieh Lin, Barlas Oguz +5
Multi-vector retrieval methods combine the merits of sparse (e.g. BM25) and dense (e.g. DPR) retrievers and have achieved state-of-the-art performance on various retrieval tasks. T…
Aggretriever: A Simple Approach to Aggregate Textual Representations for Robust Dense Passage Retrieval
Sheng-Chieh Lin, Minghan Li, Jimmy Lin
Pre-trained language models have been successful in many knowledge-intensive NLP tasks. However, recent work has shown that models such as BERT are not ``structurally ready'' to ag…
A Dense Representation Framework for Lexical and Semantic Matching
Sheng-Chieh Lin, Jimmy Lin
Lexical and semantic matching capture different successful approaches to text retrieval and the fusion of their results has proven to be more effective and robust than either alone…
Densifying Sparse Representations for Passage Retrieval by Representational Slicing
Sheng-Chieh Lin, Jimmy Lin
Learned sparse and dense representations capture different successful approaches to text retrieval and the fusion of their results has proven to be more effective and robust. Prior…
Efficiently Teaching an Effective Dense Retriever with Balanced Topic Aware Sampling
Sebastian Hofstätter, Sheng-Chieh Lin, Jheng-Hong Yang +2
A vital step towards the widespread adoption of neural retrieval models is their resource efficiency throughout the training, indexing and query workflows. The neural IR community…
Contextualized Query Embeddings for Conversational Search
Sheng-Chieh Lin, Jheng-Hong Yang, Jimmy Lin
This paper describes a compact and effective model for low-latency passage retrieval in conversational search based on learned dense representations. Prior to our work, the state-o…
Pyserini: An Easy-to-Use Python Toolkit to Support Replicable IR Research with Sparse and Dense Representations
Jimmy Lin, Xueguang Ma, Sheng-Chieh Lin +3
Pyserini is an easy-to-use Python toolkit that supports replicable IR research by providing effective first-stage retrieval in a multi-stage ranking architecture. Our toolkit is se…
Distilling Dense Representations for Ranking using Tightly-Coupled Teachers
Sheng-Chieh Lin, Jheng-Hong Yang, Jimmy Lin
We present an approach to ranking with dense representations that applies knowledge distillation to improve the recently proposed late-interaction ColBERT model. Specifically, we d…
Personalized TV Recommendation: Fusing User Behavior and Preferences
Sheng-Chieh Lin, Ting-Wei Lin, Jing-Kai Lou +2
In this paper, we propose a two-stage ranking approach for recommending linear TV programs. The proposed approach first leverages user viewing patterns regarding time and TV channe…
Multi-Stage Conversational Passage Retrieval: An Approach to Fusing Term Importance Estimation and Neural Query Rewriting
Sheng-Chieh Lin, Jheng-Hong Yang, Rodrigo Nogueira +3
Conversational search plays a vital role in conversational information seeking. As queries in information seeking dialogues are ambiguous for traditional ad-hoc information retriev…
Conversational Question Reformulation via Sequence-to-Sequence Architectures and Pretrained Language Models
Sheng-Chieh Lin, Jheng-Hong Yang, Rodrigo Nogueira +3
This paper presents an empirical study of conversational question reformulation (CQR) with sequence-to-sequence architectures and pretrained language models (PLMs). We leverage PLM…
TTTTTackling WinoGrande Schemas
Sheng-Chieh Lin, Jheng-Hong Yang, Rodrigo Nogueira +3
We applied the T5 sequence-to-sequence model to tackle the AI2 WinoGrande Challenge by decomposing each example into two input text strings, each containing a hypothesis, and using…