Related papers: Less is More: Mitigate Spurious Correlations for O…

Existing automatic evaluation metrics for open-domain dialogue response generation systems correlate poorly with human evaluation. We focus on evaluating response generation systems via response selection. To evaluate systems properly via…

While generative models such as Latent Dirichlet Allocation (LDA) have proven fruitful in topic modeling, they often require detailed assumptions and careful specification of hyperparameters. Such model complexity issues only compound when…

We present three enhancements to existing encoder-decoder models for open-domain conversational agents, aimed at effectively modeling coherence and promoting output diversity: (1) We introduce a measure of coherence as the GloVe embedding…

Recent research has revealed that machine learning models have a tendency to leverage spurious correlations that exist in the training set but may not hold true in general circumstances. For instance, a sentiment classifier may erroneously…

Causality is essential for understanding complex systems, such as the economy, the brain, and the climate. Constructing causal graphs often relies on either data-driven or expert-driven approaches, both fraught with challenges. The former…

We hypothesize that optimal system responses emerge from adaptive strategies grounded in causal and counterfactual knowledge. Counterfactual inference allows us to create hypothetical scenarios to examine the effects of alternative system…

Despite the remarkable performance of large-scale generative models in open-domain conversation, they are known to be less practical for building real-time conversation systems due to high latency. On the other hand, retrieval models could…

Pre-trained language models (PLM) have marked a huge leap in neural dialogue modeling. While PLMs are pre-trained on large-scale text corpora, they are usually fine-tuned on scarce dialogue data with specific domain knowledge and dialogue…

We present a novel response generation system that can be trained end to end on large quantities of unstructured Twitter conversations. A neural network architecture is used to address sparsity issues that arise when integrating contextual…

Models prone to spurious correlations in training data often produce brittle predictions and introduce unintended biases. Addressing this challenge typically involves methods relying on prior knowledge and group annotation to remove…

Spurious correlations threaten the validity of statistical classifiers. While model accuracy may appear high when the test data is from the same distribution as the training data, it can quickly degrade when the test distribution changes.…

Weakly supervised question answering usually has only the final answers as supervision signals while the correct solutions to derive the answers are not provided. This setting gives rise to the spurious solution problem: there may exist…

Generating responses following a desired style has great potentials to extend applications of open-domain dialogue systems, yet is refrained by lacking of parallel data for training. In this work, we explore the challenging task with…

Learning causal relationships from empirical observations is a central task in scientific research. A common method is to employ structural causal models that postulate noisy functional relations among a set of interacting variables. To…

The core of the dialogue system is to generate relevant, informative, and human-like responses based on extensive dialogue history. Recently, dialogue generation domain has seen mainstream adoption of large language models (LLMs), due to…

Causal inference remains a fundamental challenge for large language models. Recent advances in internal reasoning with large language models have sparked interest in whether state-of-the-art reasoning models can robustly perform causal…

Open-domain multi-turn conversations mainly have three features, which are hierarchical semantic structure, redundant information, and long-term dependency. Grounded on these, selecting relevant context becomes a challenge step for…

Causal discovery is to learn cause-effect relationships among variables given observational data and is important for many applications. Existing causal discovery methods assume data sufficiency, which may not be the case in many real world…

Generative seq2seq dialogue systems are trained to predict the next word in dialogues that have already occurred. They can learn from large unlabeled conversation datasets, build a deeper understanding of conversational context, and…

In the field of Natural Language Processing, there are many tasks that can be tackled effectively using the cross-entropy (CE) loss function. However, the task of dialog generation poses unique challenges for CE loss. This is because CE…