activity
20192024
most citedSentiBERT: A Transferable Transformer-Based Architecture for Compositional Sentiment Semantics

18 citations · 29 across the 6 of their papers we have counts for

collaborators
Showing cs.CLShow all

9 papers · 1 filter

cs.CL2024

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…

cs.CL2024

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…

cs.CL2024

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…

cs.CL2024

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…

cs.CL20227 cited

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…

cs.CL202018 cited

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…