3 citations · 11 across the 20 of their papers we have counts for
23 papers
VFA: Empowering Multilingual MLLMs via Vision-Free Adaptation
Yixia Li, Yaqing Shi, Zhiwen Ruan +6
Multimodal large language models have advanced rapidly, yet most remain English-centric, as scaling multilingual multimodal instruction tuning is limited by the scarcity and high c…
GIFT: Guided Fine-Tuning and Transfer for Enhancing Instruction-Tuned Language Models
Zhiwen Ruan, Yichao Du, Jianjie Zheng +6
A promising paradigm for adapting instruction-tuned language models is to learn task-specific updates on a pretrained base model and subsequently merge them into the instruction-tu…
FinSafetyBench: Evaluating LLM Safety in Real-World Financial Scenarios
Yutao Hou, Yihan Jiang, Yuhan Xie +5
Large language models (LLMs) are increasingly applied in financial scenarios. However, they may produce harmful outputs, including facilitating illegal activities or unethical beha…
Representation-Guided Parameter-Efficient LLM Unlearning
Zeguan Xiao, Lang Mo, Yun Chen +4
Large Language Models (LLMs) often memorize sensitive or harmful information, necessitating effective machine unlearning techniques. While existing parameter-efficient unlearning m…
Evaluating Memory Capability in Continuous Lifelog Scenario
Jianjie Zheng, Zhichen Liu, Zhanyu Shen +6
Nowadays, wearable devices can continuously lifelog ambient conversations, creating substantial opportunities for memory systems. However, existing benchmarks primarily focus on on…
Modeling LLM Unlearning as an Asymmetric Two-Task Learning Problem
Zeguan Xiao, Siqing Li, Yong Wang +4
Machine unlearning for large language models (LLMs) aims to remove targeted knowledge while preserving general capability. In this paper, we recast LLM unlearning as an asymmetric…
SPPO: Sequence-Level PPO for Long-Horizon Reasoning Tasks
Tianyi Wang, Yixia Li, Long Li +6
Proximal Policy Optimization (PPO) is central to aligning Large Language Models (LLMs) in reasoning tasks with verifiable rewards. However, standard token-level PPO struggles in th…
G2: Guided Generation for Enhanced Output Diversity in LLMs
Zhiwen Ruan, Yixia Li, Yefeng Liu +5
Large Language Models (LLMs) have demonstrated exceptional performance across diverse natural language processing tasks. However, these models exhibit a critical limitation in outp…
Unveiling Over-Memorization in Finetuning LLMs for Reasoning Tasks
Zhiwen Ruan, Yun Chen, Yutao Hou +3
The pretrained large language models (LLMs) are finetuned with labeled data for better instruction following ability and alignment with human values. In this paper, we study the le…
Enhancing Uncertainty Estimation in LLMs with Expectation of Aggregated Internal Belief
Zeguan Xiao, Diyang Dou, Boya Xiong +2
Large Language Models (LLMs) have achieved remarkable success across a wide range of natural language tasks, but often exhibit overconfidence and generate plausible yet incorrect a…
Beyond the Surface: Enhancing LLM-as-a-Judge Alignment with Human via Internal Representations
Peng Lai, Jianjie Zheng, Sijie Cheng +4
The growing scale of evaluation tasks has led to the widespread adoption of automated evaluation using LLMs, a paradigm known as "LLM-as-a-judge". However, improving its alignment…
Towards Bridging the Reward-Generation Gap in Direct Alignment Algorithms
Zeguan Xiao, Yun Chen, Guanhua Chen +1
Direct Alignment Algorithms (DAAs), such as Direct Preference Optimization (DPO) and Simple Preference Optimization (SimPO), have emerged as efficient alternatives to Reinforcement…
Toward Automated Robustness Evaluation of Mathematical Reasoning
Yutao Hou, Zeguan Xiao, Fei Yu +6
Large Language Models (LLMs) have demonstrated remarkable capabilities in various reasoning-intensive tasks. However, these models exhibit unexpected brittleness, often failing on…
SeTAR: Out-of-Distribution Detection with Selective Low-Rank Approximation
Yixia Li, Boya Xiong, Guanhua Chen +1
Out-of-distribution (OOD) detection is crucial for the safe deployment of neural networks. Existing CLIP-based approaches perform OOD detection by devising novel scoring functions…
MiLoRA: Harnessing Minor Singular Components for Parameter-Efficient LLM Finetuning
Hanqing Wang, Yixia Li, Shuo Wang +2
Efficient finetuning of large language models (LLMs) aims to adapt the LLMs with reduced computational and memory cost. Previous LoRA-based approaches initialize the low-rank matri…
Distract Large Language Models for Automatic Jailbreak Attack
Zeguan Xiao, Yan Yang, Guanhua Chen +1
Extensive efforts have been made before the public release of Large language models (LLMs) to align their behaviors with human values. However, even meticulously aligned LLMs remai…
StyleBART: Decorate Pretrained Model with Style Adapters for Unsupervised Stylistic Headline Generation
Hanqing Wang, Yajing Luo, Boya Xiong +2
Stylistic headline generation is the task to generate a headline that not only summarizes the content of an article, but also reflects a desired style that attracts users. As style…
PACIT: Unlocking the Power of Examples for Better In-Context Instruction Tuning
Tianci Xue, Ziqi Wang, Yixia Li +2
Instruction tuning enhances the instruction following ability of large language models by finetuning with supervised instruction data. Previous work proposes in-context instruction…
Multilingual Sentence Transformer as A Multilingual Word Aligner
Weikang Wang, Guanhua Chen, Hanqing Wang +2
Multilingual pretrained language models (mPLMs) have shown their effectiveness in multilingual word alignment induction. However, these methods usually start from mBERT or XLM-R. I…
Towards Making the Most of Multilingual Pretraining for Zero-Shot Neural Machine Translation
Guanhua Chen, Shuming Ma, Yun Chen +4
This paper demonstrates that multilingual pretraining and multilingual fine-tuning are both critical for facilitating cross-lingual transfer in zero-shot translation, where the neu…
Zero-shot Cross-lingual Transfer of Neural Machine Translation with Multilingual Pretrained Encoders
Guanhua Chen, Shuming Ma, Yun Chen +5
Previous work mainly focuses on improving cross-lingual transfer for NLU tasks with a multilingual pretrained encoder (MPE), or improving the performance on supervised machine tran…
Unsupervised Domain Adaptation of a Pretrained Cross-Lingual Language Model
Juntao Li, Ruidan He, Hai Ye +3
Recent research indicates that pretraining cross-lingual language models on large-scale unlabeled texts yields significant performance improvements over various cross-lingual and l…
Accurate Word Alignment Induction from Neural Machine Translation
Yun Chen, Yang Liu, Guanhua Chen +2
Despite its original goal to jointly learn to align and translate, prior researches suggest that Transformer captures poor word alignments through its attention mechanism. In this…