相关论文: CORE: A Retrieve-then-Edit Framework for Counterfa…

In recent years, large language models (LLMs) have shown remarkable capabilities at scale, particularly at generating text conditioned on a prompt. In our work, we investigate the use of LLMs to augment training data of small language…

For text classification tasks, finetuned language models perform remarkably well. Yet, they tend to rely on spurious patterns in training data, thus limiting their performance on out-of-distribution (OOD) test data. Among recent models…

Counterfactually-Augmented Data (CAD) has the potential to improve language models' Out-Of-Distribution (OOD) generalization capability, as CAD induces language models to exploit causal features and exclude spurious correlations. However,…

Despite large successes of recent language models on diverse tasks, they suffer from severe performance degeneration in low-resource settings with limited training data available. Many existing works tackle this problem by generating…

This paper treats gender bias latent in word embeddings. Previous mitigation attempts rely on the operationalisation of gender bias as a projection over a linear subspace. An alternative approach is Counterfactual Data Augmentation (CDA),…

Data augmentation (DA) aims to generate constrained and diversified data to improve classifiers in Low-Resource Classification (LRC). Previous studies mostly use a fine-tuned Language Model (LM) to strengthen the constraints but ignore the…

Counterfactual explanations for machine learning models are used to find minimal interventions to the feature values such that the model changes the prediction to a different output or a target output. A valid counterfactual explanation…

Generative AI has revolutionised visual content editing, empowering users to effortlessly modify images and videos. However, not all edits are equal. To perform realistic edits in domains such as natural image or medical imaging,…

A growing body of work shows that models exploit annotation artifacts to achieve state-of-the-art performance on standard crowdsourced benchmarks---datasets collected from crowdworkers to create an evaluation task---while still failing on…

Large language models exhibit complementary reasoning errors: on the same instance, one model may succeed with a particular decomposition while another fails. We propose Collaborative Reasoning (CORE), a training-time collaboration…

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…

Counterfactual examples have proven to be valuable in the field of natural language processing (NLP) for both evaluating and improving the robustness of language models to spurious correlations in datasets. Despite their demonstrated…

Counterfactual explanation is a form of interpretable machine learning that generates perturbations on a sample to achieve the desired outcome. The generated samples can act as instructions to guide end users on how to observe the desired…

Retrieval-augmented generation (RAG) frameworks enable large language models (LLMs) to retrieve relevant information from a knowledge base and incorporate it into the context for generating responses. This mitigates hallucinations and…

The reliance of text classifiers on spurious correlations can lead to poor generalization at deployment, raising concerns about their use in safety-critical domains such as healthcare. In this work, we propose to use counterfactual data…

Counterfactual explanations are viewed as an effective way to explain machine learning predictions. This interest is reflected by a relatively young literature with already dozens of algorithms aiming to generate such explanations. These…

With the widespread accumulation of observational data, researchers obtain a new direction to learn counterfactual effects in many domains (e.g., health care and computational advertising) without Randomized Controlled Trials(RCTs).…

Ensuring truthfulness in large language models (LLMs) remains a critical challenge for reliable text generation. While supervised fine-tuning and reinforcement learning with human feedback have shown promise, they require a substantial…

Evaluating the quality of documents is essential for filtering valuable content from the current massive amount of information. Conventional approaches typically rely on a single score as a supervision signal for training content quality…

We present a novel generative method for producing unseen and plausible counterfactual examples for reinforcement learning (RL) agents based upon outcome variables that characterize agent behavior. Our approach uses a variational…