Challenge: Existing methods for posterior calibration return uncalibrated estimations of class posteriors, thus leading to poorer generalization.
Approach: They propose an end-to-end trained calibrator that directly optimizes the objective while minimizing the difference between predicted and empirical posterior probabilities.
Outcome: The proposed calibrator reduces calibration error and improves performance on benchmark NLP classification tasks.

Similar Papers

Predicting generalization performance with correctness discriminators (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing models estimate accuracy of models on unlabeled test data, but they hide their own uncertainty.
Approach: They propose a model that establishes upper and lower bounds on the accuracy without requiring gold labels for the unseen data.
Outcome: The proposed model establishes upper and lower bounds on accuracy without requiring gold labels for the unseen data.
Calibrating Structured Output Predictors for Natural Language Processing (2020.acl-main)

Copied to clipboard

Challenge: Several modern machine-learning based NLP systems can provide a confidence score with their output predictions.
Approach: They propose a general calibration scheme for output entities of interest in NLP applications that can be used to calibrate confidence scores.
Outcome: The proposed calibration scheme outperforms current calibration techniques for Named Entity Recognition, Part-of-speech tagging and Question Answering systems.
Crossing Domains without Labels: Distant Supervision for Term Extraction (2025.emnlp-industry)

Copied to clipboard

Challenge: Current state-of-the-art methods require expensive human annotation and struggle with domain transfer, limiting their practical deployment.
Approach: They propose a benchmark spanning seven diverse domains to evaluate ATE performance . they propose psuedo-labels and post-hoc heuristics to ensure generalizability .
Outcome: The proposed model outperforms supervised cross-domain encoder models and few-shot learning baselines on the document- and corpus-levels and its GPT-4o teacher on the benchmark.
Calibration of Pre-trained Transformers (2020.emnlp-main)

Copied to clipboard

Challenge: Pre-trained Transformers dominate benchmark tasks but use a large number of self-attention heads across many layers in a way that is difficult to unpack.
Approach: They analyze pre-trained Transformer models' posterior probabilities to determine whether they are calibrated for three tasks: natural language inference, paraphrase detection, and commonsense reasoning.
Outcome: The models are calibrated in-domain and out-of-domain, and their calibration error out-domain can be as much as 3.5x lower.
Making Pre-trained Language Models both Task-solvers and Self-calibrators (2023.findings-acl)

Copied to clipboard

Challenge: Existing work shows that pre-trained language models can be effective for high-stake applications, but they become overconfident in their wrong predictions.
Approach: They propose to use extra data to train pre-trained language models to effectively utilize training samples to make them both task-solvers and self-calibrators.
Outcome: The proposed method can be used in three downstream applications, including selective classification, adversarial defense, and model cascading.
Discriminatively-Tuned Generative Classifiers for Robust Natural Language Inference (2020.emnlp-main)

Copied to clipboard

Challenge: Recent work has shown advantages of generative classifiers in terms of data efficiency and robustness.
Approach: They propose a generative classifier for natural language inference (NLI) they compare it to discriminative models and large-scale pretrained models like BERT .
Outcome: The proposed classifier outperforms discriminative and pretrained baselines across several challenging NLI experimental settings, including small training sets, imbalanced label distributions, and label noise.
Pre-training Is (Almost) All You Need: An Application to Commonsense Reasoning (2020.acl-main)

Copied to clipboard

Challenge: Existing methods for solving common NLP tasks rely on fine-tuning of pre-trained transformer models.
Approach: They propose a scoring method that casts a plausibility ranking task in full-text format without fine-tuning . they use masked language modeling head tuned during pre-training phase to exploit this method .
Outcome: The proposed method produces strong baselines comparable to supervised approaches.
Noise Stability Regularization for Improving BERT Fine-tuning (2021.naacl-main)

Copied to clipboard

Challenge: Recent studies show that fine-tuning pre-trained language models is unstable when there are only a small number of training samples available.
Approach: They propose to use a method to regularize noise in deep nets to improve fine-tuning on NLP tasks.
Outcome: The proposed method improves fine-tuning on natural language processing tasks by incorporating noise to the input and demonstrating generalizability and stability.
Calibrated Speculative Decoding: Frequency-Guided Candidate Selection for Efficient Inference (2026.acl-long)

Copied to clipboard

Challenge: Speculative decoding (SD) is a powerful and efficient way to accelerate autoregressive generation.
Approach: They propose a training-free framework that recovers valid tokens discarded by standard verification . they use online correction memory and Semantic Consistency Gating to analyze rejections .
Outcome: The proposed framework outperforms existing methods and achieves peak throughput speedup of 2.33x.
How Far Is Too Far? Studying the Effects of Domain Discrepancy on Masked Language Models (2024.lrec-main)

Copied to clipboard

Challenge: Pre-trained masked language models perform strongly on a wide variety of NLP tasks.
Approach: They propose a mechanism to quantify the difference in domains between the pre-trained model and the task and partition it using a cloze task.
Outcome: The proposed model performs better on openly available e-commerce datasets than the original model on scientific and biomedical datasets.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations