18 citations · 43 across the 12 of their papers we have counts for
12 papers
T-REG: Preference Optimization with Token-Level Reward Regularization
Wenxuan Zhou, Shujian Zhang, Lingxiao Zhao +1
Reinforcement learning from human feedback (RLHF) has been crucial in aligning large language models (LLMs) with human values. Traditionally, RLHF involves generating responses to…
Attribute Controlled Fine-tuning for Large Language Models: A Case Study on Detoxification
Tao Meng, Ninareh Mehrabi, Palash Goyal +6
We propose a constraint learning schema for fine-tuning Large Language Models (LLMs) with attribute control. Given a training corpus and control criteria formulated as a sequence-l…
Control Large Language Models via Divide and Conquer
Bingxuan Li, Yiwei Wang, Tao Meng +2
This paper investigates controllable generation for large language models (LLMs) with prompt-based control, focusing on Lexically Constrained Generation (LCG). We systematically ev…
Monotonic Paraphrasing Improves Generalization of Language Model Prompting
Qin Liu, Fei Wang, Nan Xu +3
Performance of large language models (LLMs) may vary with different prompts or instructions of even the same task. One commonly recognized factor for this phenomenon is the model's…
On the Paradox of Learning to Reason from Data
Honghua Zhang, Liunian Harold Li, Tao Meng +2
Logical reasoning is needed in a wide range of NLP tasks. Can a BERT model be trained end-to-end to solve logical reasoning problems presented in natural language? We attempt to an…
Controllable Text Generation with Neurally-Decomposed Oracle
Tao Meng, Sidi Lu, Nanyun Peng +1
We propose a general and efficient framework to control auto-regressive generation models with NeurAlly-Decomposed Oracle (NADO). Given a pre-trained base language model and a sequ…
InsNet: An Efficient, Flexible, and Performant Insertion-based Text Generation Model
Sidi Lu, Tao Meng, Nanyun Peng
We propose InsNet, an expressive insertion-based text generator with efficient training and flexible decoding (parallel or sequential). Unlike most existing insertion-based text ge…
An Integer Linear Programming Framework for Mining Constraints from Data
Tao Meng, Kai-Wei Chang
Structured output prediction problems (e.g., sequential tagging, hierarchical multi-class classification) often involve constraints over the output label space. These constraints i…
SentiBERT: A Transferable Transformer-Based Architecture for Compositional Sentiment Semantics
Da Yin, Tao Meng, Kai-Wei Chang
We propose SentiBERT, a variant of BERT that effectively captures compositional sentiment semantics. The model incorporates contextualized representation with binary constituency p…
Mitigating Gender Bias Amplification in Distribution by Posterior Regularization
Shengyu Jia, Tao Meng, Jieyu Zhao +1
Advanced machine learning techniques have boosted the performance of natural language processing. Nevertheless, recent studies, e.g., Zhao et al. (2017) show that these techniques…
On the Robustness of Language Encoders against Grammatical Errors
Fan Yin, Quanyu Long, Tao Meng +1
We conduct a thorough study to diagnose the behaviors of pre-trained language encoders (ELMo, BERT, and RoBERTa) when confronted with natural grammatical errors. Specifically, we c…
Target Language-Aware Constrained Inference for Cross-lingual Dependency Parsing
Tao Meng, Nanyun Peng, Kai-Wei Chang
Prior work on cross-lingual dependency parsing often focuses on capturing the commonalities between source and target languages and overlooks the potential of leveraging linguistic…