相关论文: Why Are You Wrong? Counterfactual Explanations for…

We propose a large language model explainability technique for obtaining faithful natural language explanations by grounding the explanations in a reasoning process. When converted to a sequence of tokens, the outputs of the reasoning…

Existing models which generate textual explanations enforce task relevance through a discriminative term loss function, but such mechanisms only weakly constrain mentioned object parts to actually be present in the image. In this paper, a…

The tracking-by-detection framework requires a set of positive and negative training samples to learn robust tracking models for precise localization of target objects. However, existing tracking models mostly treat different samples…

Counterfactual instances offer human-interpretable insight into the local behaviour of machine learning models. We propose a general framework to generate sparse, in-distribution counterfactual model explanations which match a desired…

This research addresses a fundamental question in AI: whether large language models truly understand concepts or simply recognize patterns. The authors propose bidirectional reasoning,the ability to apply transformations in both directions…

Semantic understanding of 3D objects is crucial in many applications such as object manipulation. However, it is hard to give a universal definition of point-level semantics that everyone would agree on. We observe that people have a…

Autoregressive language models, pretrained using large text corpora to do well on next word prediction, have been successful at solving many downstream tasks, even with zero-shot usage. However, there is little theoretical understanding of…

Negation is a core construction in natural language. Despite being very successful on many tasks, state-of-the-art pre-trained language models often handle negation incorrectly. To improve language models in this regard, we propose to…

As robots begin to cohabit with humans in semi-structured environments, the need arises to understand instructions involving rich variability---for instance, learning to ground symbols in the physical world. Realistically, this task must…

Counterfactual explanation is a common class of methods to make local explanations of machine learning decisions. For a given instance, these methods aim to find the smallest modification of feature values that changes the predicted…

A highly accurate but overconfident model is ill-suited for deployment in critical applications such as healthcare and autonomous driving. The classification outcome should reflect a high uncertainty on ambiguous in-distribution samples…

Causal explanations of the predictions of NLP systems are essential to ensure safety and establish trust. Yet, existing methods often fall short of explaining model predictions effectively or efficiently and are often model-specific. In…

Current pre-trained language models have enabled remarkable improvements in downstream tasks, but it remains difficult to distinguish effects of statistical correlation from more systematic logical reasoning grounded on the understanding of…

We address the problem of jointly learning vision and language to understand the object in a fine-grained manner. The key idea of our approach is the use of object descriptions to provide the detailed understanding of an object. Based on…

Chat-based language models are designed to be helpful, yet they should not comply with every user request. While most existing work primarily focuses on refusal of "unsafe" queries, we posit that the scope of noncompliance should be…

When captioning an image, people describe objects in diverse ways, such as by using different terms and/or including details that are perceptually noteworthy to them. Descriptions can be especially unique across languages and cultures.…

Vision-language models have demonstrated impressive capabilities in generating 2D images under various conditions; however, the success of these models is largely enabled by extensive, readily available pretrained foundation models.…

We propose an approach to predict the 3D shape and pose for the objects present in a scene. Existing learning based methods that pursue this goal make independent predictions per object, and do not leverage the relationships amongst them.…

Vision-and-language (V\&L) reasoning necessitates perception of visual concepts such as objects and actions, understanding semantics and language grounding, and reasoning about the interplay between the two modalities. One crucial aspect of…

Existing visual explanation generating agents learn to fluently justify a class prediction. However, they may mention visual attributes which reflect a strong class prior, although the evidence may not actually be in the image. This is…