3 citations · 6 across the 16 of their papers we have counts for
19 papers
Rubrics from the Task, Verdicts from Evidence: Pointwise Rubric Rewards with Tool-Augmented Judges
Tianci Liu, Haoyu Wang
Rubric-based reward models (RMs) evaluate responses against explicit criteria. However, existing methods often derive criteria from observed response candidates, introducing respon…
Personalization as Inverse Planning: Learning Latent Design Intents for Agentic Slide Generation via Structural Denoising
Tianci Liu, Zihan Dong, Linjun Zhang +5
Slide design requires personalizing both deck themes and page layouts. Yet, current AI agent-based methods struggle with fine-grained, page-level design. Solely relying on prespeci…
RIMS: Preference Optimization via Smoothed Multi-pair Aggregation for Small-Scale LLM Retrieval-Augmented Generation
Pei Tian, Zihan Dong, Tianci Liu +2
Small-scale language models (SLMs) are attractive for retrieval-augmented generation (RAG) in resource-constrained settings, but their limited capacity makes them highly sensitive…
RUBRIC-ARROW: Alternating Pointwise Rubric Reward Modeling for LLM Post-training in Non-verifiable Domains
Haoxiang Jiang, Zihan Dong, Tianci Liu +5
Pointwise reward modeling offers critical signals for LLM post-training, yet struggles with absolute scoring in subjective, non-verifiable settings. Rubric-based methods address th…
Alternating Reinforcement Learning for Rubric-Based Reward Modeling in Non-Verifiable LLM Post-Training
Ran Xu, Tianci Liu, Zihan Dong +6
Standard reward models typically predict scalar scores that fail to capture the multifaceted nature of response quality in non-verifiable domains, such as creative writing or open-…
OpenRubrics: Towards Scalable Synthetic Rubric Generation for Reward Modeling and LLM Alignment
Tianci Liu, Ran Xu, Tony Yu +4
Reward modeling lies at the core of reinforcement learning from human feedback (RLHF), yet most existing reward models rely on scalar or pairwise judgments that fail to capture the…
Unlocking Efficient, Scalable, and Continual Knowledge Editing with Basis-Level Representation Fine-Tuning
Tianci Liu, Ruirui Li, Yunzhe Qi +8
Large language models (LLMs) have achieved remarkable performance on various natural language tasks. However, they are trained on static corpora and their knowledge can become outd…
RoseRAG: Robust Retrieval-augmented Generation with Small-scale LLMs via Margin-aware Preference Optimization
Tianci Liu, Haoxiang Jiang, Tianze Wang +5
Large language models (LLMs) have achieved impressive performance but face high computational costs and latency, limiting their deployment in resource-constrained settings. In cont…
Mitigating Heterogeneous Token Overfitting in LLM Knowledge Editing
Tianci Liu, Ruirui Li, Zihan Dong +6
Large language models (LLMs) have achieved remarkable performance on various natural language tasks. However, they are trained on static corpora and their knowledge can become outd…
PEANuT: Parameter-Efficient Adaptation with Weight-aware Neural Tweakers
Yibo Zhong, Haoxiang Jiang, Lincan Li +5
Fine-tuning large pre-trained foundation models often yields excellent downstream performance but is prohibitively expensive when updating all parameters. Parameter-efficient fine-…
Counterfactual Fairness by Combining Factual and Counterfactual Predictions
Zeyu Zhou, Tianci Liu, Ruqi Bai +3
In high-stake domains such as healthcare and hiring, the role of machine learning (ML) in decision-making raises significant fairness concerns. This work focuses on Counterfactual…
FIARSE: Model-Heterogeneous Federated Learning via Importance-Aware Submodel Extraction
Feijie Wu, Xingchen Wang, Yaqing Wang +3
In federated learning (FL), accommodating clients' varied computational capacities poses a challenge, often limiting the participation of those with constrained resources in global…
RoseLoRA: Row and Column-wise Sparse Low-rank Adaptation of Pre-trained Language Model for Knowledge Editing and Fine-tuning
Haoyu Wang, Tianci Liu, Ruirui Li +3
Pre-trained language models, trained on large-scale corpora, demonstrate strong generalizability across various NLP tasks. Fine-tuning these models for specific tasks typically inv…
LIDAO: Towards Limited Interventions for Debiasing (Large) Language Models
Tianci Liu, Haoyu Wang, Shiyang Wang +2
Large language models (LLMs) have achieved impressive performance on various natural language generation tasks. Nonetheless, they suffer from generating negative and harmful conten…
Towards Poisoning Fair Representations
Tianci Liu, Haoyu Wang, Feijie Wu +4
Fair machine learning seeks to mitigate model prediction bias against certain demographic subgroups such as elder and female. Recently, fair representation learning (FRL) trained b…
SimFair: A Unified Framework for Fairness-Aware Multi-Label Classification
Tianci Liu, Haoyu Wang, Yaqing Wang +3
Recent years have witnessed increasing concerns towards unfair decisions made by machine learning algorithms. To improve fairness in model decisions, various fairness notions have…
Optimization for Amortized Inverse Problems
Tianci Liu, Tong Yang, Quan Zhang +1
Incorporating a deep generative model as the prior distribution in inverse problems has established substantial success in reconstructing images from corrupted observations. Notwit…
Density Regression and Uncertainty Quantification with Bayesian Deep Noise Neural Networks
Daiwei Zhang, Tianci Liu, Jian Kang
Deep neural network (DNN) models have achieved state-of-the-art predictive accuracy in a wide range of supervised learning applications. However, accurately quantifying the uncerta…
An Empirical Comparison of GANs and Normalizing Flows for Density Estimation
Tianci Liu, Jeffrey Regier
Generative adversarial networks (GANs) and normalizing flows are both approaches to density estimation that use deep neural networks to transform samples from an uninformative prio…