24 citations · 32 across the 10 of their papers we have counts for
10 papers
YouZhi: Towards High-Concurrency Financial LLMs via Adaptive GQA-to-MLA Transition
PSBC LLM Team, Huawei LLM Team, Ruihan Long +56
Large language models (LLMs) drive significant financial innovations, yet their high-concurrency deployment is severely bottlenecked by KV cache memory overhead, which inflates inf…
Ref-Long: Benchmarking the Long-context Referencing Capability of Long-context Language Models
Junjie Wu, Gefei Gu, Yanan Zheng +2
Long-context language models (LCLMs) have exhibited impressive capabilities in long-context understanding tasks. Among these, long-context referencing -- a crucial task that requir…
SitEmb-v1.5: Improved Context-Aware Dense Retrieval for Semantic Association and Long Story Comprehension
Junjie Wu, Jiangnan Li, Yuqing Li +6
Retrieval-augmented generation (RAG) over long documents typically involves splitting the text into smaller chunks, which serve as the basic units for retrieval. However, due to de…
Understanding LLMs' Fluid Intelligence Deficiency: An Analysis of the ARC Task
Junjie Wu, Mo Yu, Lemao Liu +2
While LLMs have exhibited strong performance on various NLP tasks, it is noteworthy that most of these tasks rely on utilizing the vast amount of knowledge encoded in LLMs' paramet…
The Stochastic Parrot on LLM's Shoulder: A Summative Assessment of Physical Concept Understanding
Mo Yu, Lemao Liu, Junjie Wu +5
In a systematic way, we investigate a widely asked question: Do LLMs really understand what they say?, which relates to the more familiar term Stochastic Parrot. To this end, we pr…
Unified Triplet-Level Hallucination Evaluation for Large Vision-Language Models
Junjie Wu, Tsz Ting Chung, Kai Chen +1
Despite the outstanding performance in vision-language reasoning, Large Vision-Language Models (LVLMs) might generate hallucinated contents that do not exist in the given image. Mo…
Rethinking Targeted Adversarial Attacks For Neural Machine Translation
Junjie Wu, Lemao Liu, Wei Bi +1
Targeted adversarial attacks are widely used to evaluate the robustness of neural machine translation systems. Unfortunately, this paper first identifies a critical issue in the ex…
Towards General Error Diagnosis via Behavioral Testing in Machine Translation
Junjie Wu, Lemao Liu, Dit-Yan Yeung
Behavioral testing offers a crucial means of diagnosing linguistic errors and assessing capabilities of NLP models. However, applying behavioral testing to machine translation (MT)…
SCAT: Robust Self-supervised Contrastive Learning via Adversarial Training for Text Classification
Junjie Wu, Dit-Yan Yeung
Despite their promising performance across various natural language processing (NLP) tasks, current NLP systems are vulnerable to textual adversarial attacks. To defend against the…
Conversations Gone Alright: Quantifying and Predicting Prosocial Outcomes in Online Conversations
Jiajun Bao, Junjie Wu, Yiming Zhang +2
Online conversations can go in many directions: some turn out poorly due to antisocial behavior, while others turn out positively to the benefit of all. Research on improving onlin…