activity
20212024
most citedBridging Subword Gaps in Pretrain-Finetune Paradigm for Natural Language Generation

3 citations · 4 across the 6 of their papers we have counts for

collaborators
Showing cs.CLShow all

8 papers · 1 filter

cs.CL2024

Enhanced Language Model Truthfulness with Learnable Intervention and Uncertainty Expression

Farima Fatahi Bayat, Xin Liu, H. V. Jagadish +1

Large language models (LLMs) can generate long-form and coherent text, yet they often hallucinate facts, which undermines their reliability. To mitigate this issue, inference-time…

cs.CL2024

Enhancing Language Model Factuality via Activation-Based Confidence Calibration and Guided Decoding

Xin Liu, Farima Fatahi Bayat, Lu Wang

Calibrating language models (LMs) aligns their generation confidence with the actual likelihood of answer correctness, which can inform users about LMs' reliability and mitigate ha…

cs.CL2023

IBADR: an Iterative Bias-Aware Dataset Refinement Framework for Debiasing NLU models

Xiaoyue Wang, Xin Liu, Lijie Wang +3

As commonly-used methods for debiasing natural language understanding (NLU) models, dataset refinement approaches heavily rely on manual data analysis, and thus maybe unable to cov…

cs.CL2023

LitCab: Lightweight Language Model Calibration over Short- and Long-form Responses

Xin Liu, Muhammad Khalifa, Lu Wang

A model is considered well-calibrated when its probability estimate aligns with the actual likelihood of the output being correct. Calibrating language models (LMs) is crucial, as…

cs.CL20231 cited

A Simple yet Effective Self-Debiasing Framework for Transformer Models

Xiaoyue Wang, Lijie Wang, Xin Liu +3

Current Transformer-based natural language understanding (NLU) models heavily rely on dataset biases, while failing to handle real-world out-of-distribution (OOD) instances. Many m…

cs.CL2023

BOLT: Fast Energy-based Controlled Text Generation with Tunable Biases

Xin Liu, Muhammad Khalifa, Lu Wang

Energy-based models (EBMs) have gained popularity for controlled text generation due to their high applicability to a wide range of constraints. However, sampling from EBMs is non-…