Zobrazeno 1 - 10
of 98
pro vyhledávání: '"Ji, Ziwei"'
Large language models (LLMs) exhibit hallucinations in long-form question-answering tasks across various domains and wide applications. Current hallucination detection and mitigation datasets are limited in domains and sizes, which struggle to scale
Externí odkaz:
http://arxiv.org/abs/2407.04693
Autor:
Ji, Ziwei, Chen, Delong, Ishii, Etsuko, Cahyawijaya, Samuel, Bang, Yejin, Wilie, Bryan, Fung, Pascale
The hallucination problem of Large Language Models (LLMs) significantly limits their reliability and trustworthiness. Humans have a self-awareness process that allows us to recognize what we don't know when faced with queries. Inspired by this, our p
Externí odkaz:
http://arxiv.org/abs/2407.03282
Autor:
Ji, Ziwei, Jain, Himanshu, Veit, Andreas, Reddi, Sashank J., Jayasumana, Sadeep, Rawat, Ankit Singh, Menon, Aditya Krishna, Yu, Felix, Kumar, Sanjiv
Cross-Encoder (CE) and Dual-Encoder (DE) models are two fundamental approaches for query-document relevance in information retrieval. To predict relevance, CE models use joint query-document embeddings, while DE models maintain factorized query and d
Externí odkaz:
http://arxiv.org/abs/2406.17968
Reducing the `$\textit{hallucination}$' problem of Large Language Models (LLMs) is crucial for their wide applications. A comprehensive and fine-grained measurement of the hallucination is the first key step for the governance of this issue but is un
Externí odkaz:
http://arxiv.org/abs/2405.20315
Autor:
Cahyawijaya, Samuel, Chen, Delong, Bang, Yejin, Khalatbari, Leila, Wilie, Bryan, Ji, Ziwei, Ishii, Etsuko, Fung, Pascale
The widespread application of Large Language Models (LLMs) across various tasks and fields has necessitated the alignment of these models with human values and preferences. Given various approaches of human value alignment, ranging from Reinforcement
Externí odkaz:
http://arxiv.org/abs/2404.07900
Inference, especially those derived from inductive processes, is a crucial component in our conversation to complement the information implicitly or explicitly conveyed by a speaker. While recent large language models show remarkable advances in infe
Externí odkaz:
http://arxiv.org/abs/2310.12467
Large language models (LLMs) have shown promise for generative and knowledge-intensive tasks including question-answering (QA) tasks. However, the practical deployment still faces challenges, notably the issue of "hallucination", where models generat
Externí odkaz:
http://arxiv.org/abs/2310.06271
Negative Object Presence Evaluation (NOPE) to Measure Object Hallucination in Vision-Language Models
Object hallucination poses a significant challenge in vision-language (VL) models, often leading to the generation of nonsensical or unfaithful responses with non-existent objects. However, the absence of a general measurement for evaluating object h
Externí odkaz:
http://arxiv.org/abs/2310.05338
Autor:
Goyal, Sachin, Ji, Ziwei, Rawat, Ankit Singh, Menon, Aditya Krishna, Kumar, Sanjiv, Nagarajan, Vaishnavh
Language models generate responses by producing a series of tokens in immediate succession: the $(K+1)^{th}$ token is an outcome of manipulating $K$ hidden vectors per layer, one vector per preceding token. What if instead we were to let the model ma
Externí odkaz:
http://arxiv.org/abs/2310.02226
Query-Focused Meeting Summarization (QFMS) aims to generate a summary of a given meeting transcript conditioned upon a query. The main challenges for QFMS are the long input text length and sparse query-relevant information in the meeting transcript.
Externí odkaz:
http://arxiv.org/abs/2309.02105