117 citations · 529 across the 70 of their papers we have counts for
14 papers · 1 filter
Thinking Forward and Backward: Multi-Objective Reinforcement Learning for Retrieval-Augmented Reasoning
Wenda Wei, Yu-An Liu, Ruqing Zhang +6
Retrieval-augmented generation (RAG) has proven to be effective in mitigating hallucinations in large language models, yet its effectiveness remains limited in complex, multi-step…
A Claim Decomposition Benchmark for Long-form Answer Verification
Zhihao Zhang, Yixing Fan, Ruqing Zhang +1
The advancement of LLMs has significantly boosted the performance of complex long-form question answering tasks. However, one prominent issue of LLMs is the generated "hallucinatio…
On the Capacity of Citation Generation by Large Language Models
Haosheng Qian, Yixing Fan, Ruqing Zhang +1
Retrieval-augmented generation (RAG) appears as a promising method to alleviate the "hallucination" problem in large language models (LLMs), since it can incorporate external trace…
Controlling Risk of Retrieval-augmented Generation: A Counterfactual Prompting Framework
Lu Chen, Ruqing Zhang, Jiafeng Guo +2
Retrieval-augmented generation (RAG) has emerged as a popular solution to mitigate the hallucination issues of large language models. However, existing studies on RAG seldom addres…
Pretraining Data Detection for Large Language Models: A Divergence-based Calibration Method
Weichao Zhang, Ruqing Zhang, Jiafeng Guo +3
As the scale of training corpora for large language models (LLMs) grows, model developers become increasingly reluctant to disclose details on their data. This lack of transparency…
A Unified Causal View of Instruction Tuning
Lu Chen, Wei Huang, Ruqing Zhang +3
Instruction tuning on a mixture of tasks has improved zero-shot capabilities in natural language processing (NLP). Nevertheless, existing methods often learn features that exhibit…
RIGHT: Retrieval-augmented Generation for Mainstream Hashtag Recommendation
Run-Ze Fan, Yixing Fan, Jiangui Chen +3
Automatic mainstream hashtag recommendation aims to accurately provide users with concise and popular topical hashtags before publication. Generally, mainstream hashtag recommendat…
Inducing Causal Structure for Abstractive Text Summarization
Lu Chen, Ruqing Zhang, Wei Huang +3
The mainstream of data-driven abstractive summarization models tends to explore the correlations rather than the causal relationships. Among such correlations, there can be spuriou…
CorpusBrain: Pre-train a Generative Retrieval Model for Knowledge-Intensive Language Tasks
Jiangui Chen, Ruqing Zhang, Jiafeng Guo +3
Knowledge-intensive language tasks (KILT) usually require a large body of information to provide correct answers. A popular paradigm to solve this problem is to combine a search sy…
A Simple Contrastive Learning Objective for Alleviating Neural Text Degeneration
Shaojie Jiang, Ruqing Zhang, Svitlana Vakulenko +1
The cross-entropy objective has proved to be an all-purpose training objective for autoregressive language models (LMs). However, without considering the penalization of problemati…
GERE: Generative Evidence Retrieval for Fact Verification
Jiangui Chen, Ruqing Zhang, Jiafeng Guo +2
Fact verification (FV) is a challenging task which aims to verify a claim using multiple evidential sentences from trustworthy corpora, e.g., Wikipedia. Most existing approaches fo…
Query Understanding via Intent Description Generation
Ruqing Zhang, Jiafeng Guo, Yixing Fan +2
Query understanding is a fundamental problem in information retrieval (IR), which has attracted continuous attention through the past decades. Many different tasks have been propos…
Outline Generation: Understanding the Inherent Content Structure of Documents
Ruqing Zhang, Jiafeng Guo, Yixing Fan +2
In this paper, we introduce and tackle the Outline Generation (OG) task, which aims to unveil the inherent content structure of a multi-paragraph document by identifying its potent…
Spherical Paragraph Model
Ruqing Zhang, Jiafeng Guo, Yanyan Lan +2
Representing texts as fixed-length vectors is central to many language processing tasks. Most traditional methods build text representations based on the simple Bag-of-Words (BoW)…