Challenge: Neural dialogue belief trackers that take uncertainty into account are often overconfident in their decisions and therefore less robust.
Approach: They propose to use different uncertainty measures in neural belief tracking to integrate uncertainty into the feature space of the policy and train policies through interaction with a user simulator.
Outcome: The proposed approach improves both performance and robustness of the downstream dialogue policy.

Similar Papers

Knowing What You Know: Calibrating Dialogue Belief State Distributions via Ensembles (2020.findings-emnlp)

Copied to clipboard

Challenge: Current models for dialogue state tracking only achieve 55% accuracy . however, they lack in performance compared to belief trackers and do not produce well calibrated distributions.
Approach: They propose to calibrate a model for dialogue belief trackers to measure dialogue state accuracy.
Outcome: The proposed model outperforms existing models in terms of accuracy and accuracy.
Fully Statistical Neural Belief Tracking (P18-2)

Copied to clipboard

Challenge: Existing framework for a dialogue state tracking model requires an expensive manual retuning step .
Approach: They propose to improve existing NBT model by removing a manual retuning step . they propose two different statistical update mechanisms to improve model performance .
Outcome: The proposed model achieves competitive performance and provides a robust framework for building resource-light DST models.
Deal, or no deal (or who knows)? Forecasting Uncertainty in Conversations using Large Language Models (2024.findings-acl)

Copied to clipboard

Challenge: Effective interlocutors account for the uncertain goals, beliefs, and emotions of others.
Approach: They propose to calibrate language models to better represent outcome uncertainty . they propose to use two methods to calibrated small open-source models .
Outcome: The proposed fine-tuning strategies can calibrate smaller open-source models to beat pre-trained models 10x their size.
“None of the Above”: Measure Uncertainty in Dialog Response Retrieval (2020.acl-main)

Copied to clipboard

Challenge: End-to-end (E2E) dialog retrieval models jointly encode a dialog and a candidate response, assuming the ground truth is always present in the candidate set.
Approach: They propose to capture the original retrieval model's confidence concerning the best prediction using trivial additional computation.
Outcome: The proposed model can capture the model's confidence concerning the best prediction using trivial additional computation.
Investigating the Impact of Model Instability on Explanations and Uncertainty (2024.findings-acl)

Copied to clipboard

Challenge: Explainable AI methods are typically evaluated holistically, but small perturbations to inputs can vastly distort explanations.
Approach: They artificially simulate epistemic uncertainty in text input by introducing noise at inference time and measure the effect on the output of pre-trained language models.
Outcome: The proposed model can detect salient tokens when uncertain, but it is not reliable when small perturbations are exposed during training.
Dialogue State Tracking with Incremental Reasoning (2021.tacl-1)

Copied to clipboard

Challenge: Empirical results show that our method outperforms the state-of-the-art methods in terms of joint belief accuracy.
Approach: They propose to track dialogue states gradually with reasoning over dialogue turns using the back-end data.
Outcome: Empirical results show that the proposed method outperforms state-of-the-art methods in terms of joint belief accuracy for a large-scale human–human dialogue dataset.
On the Interaction of Belief Bias and Explanations (2021.findings-acl)

Copied to clipboard

Challenge: Existing methods to evaluate explainability fail to account for belief biases affecting human performance . previous studies have shown that neural models can make confident predictions relying on artifacts .
Approach: They propose to account for belief bias in explainability by using models of varying quality and adversarial examples.
Outcome: The proposed methods show that results change when using models of varying quality and adversarial examples.
On Uncertainty Calibration and Selective Generation in Probabilistic Neural Summarization: A Benchmark Study (2023.findings-emnlp)

Copied to clipboard

Challenge: Modern deep models for summarization generate miscalibrated predictive uncertainty, compromising reliability and trustworthiness in real-world applications.
Approach: They propose to use probabilistic methods to improve the uncertainty quality of neural summarization models by using three large-scale benchmarks with varying difficulty.
Outcome: The proposed methods consistently improve the model’s generation and uncertainty quality, leading to improved selective generation performance (i.e., abstaining from low-quality summaries) in practice.
Relying on the Unreliable: The Impact of Language Models’ Reluctance to Express Uncertainty (2024.acl-long)

Copied to clipboard

Challenge: a pivotal aspect of fostering reliable human-AI interactions lies in the apt communication of model confidences.
Approach: They examine how LMs incorporate confidence in responses via natural language . they also examine how downstream users behave in response to LM-articulated uncertainties .
Outcome: The proposed model overconfidences are high in LMs, and humans are biased against uncertainty-rich texts.
Increasing Faithfulness in Knowledge-Grounded Dialogue with Controllable Features (2021.acl-long)

Copied to clipboard

Challenge: Existing systems that strive to be informative teachers are difficult to build . knowledge grounded dialogue systems are difficult because of limited training objectives .
Approach: They propose to train a generative neural dialogue model that is controlled to stay faithful to evidence . they propose to use additional inputs to generate more objective responses .
Outcome: The proposed model produces responses that are perceived by humans to be objective and faithful to evidence.

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