Related papers: Unified Pragmatic Models for Generating and Follow…

We study the interpretability issue of task-oriented dialogue systems in this paper. Previously, most neural-based task-oriented dialogue systems employ an implicit reasoning strategy that makes the model predictions uninterpretable to…

The ability to combine linguistic guidance from others with direct experience is central to human development, enabling safe and rapid learning in new environments. How do people integrate these two sources of knowledge, and how might AI…

Referring expressions are natural language constructions used to identify particular objects within a scene. In this paper, we propose a unified framework for the tasks of referring expression comprehension and generation. Our model is…

Prompt engineering is widely used to shape large language model behavior, yet it is often treated as a practical heuristic rather than as a form of natural-language control. This paper develops a cognitive-semantic account in which prompts…

Explanations shed light on a machine learning model's rationales and can aid in identifying deficiencies in its reasoning process. Explanation generation models are typically trained in a supervised way given human explanations. When such…

Transformers have been shown to emulate logical deduction over natural language theories (logical rules expressed in natural language), reliably assigning true/false labels to candidate implications. However, their ability to generate…

Language Generation Models produce words based on the previous context. Although existing methods offer input attributions as explanations for a model's prediction, it is still unclear how prior words affect the model's decision throughout…

Prompts have been shown to be an effective method to adapt a frozen Pretrained Language Model (PLM) to perform well on downstream tasks. Prompts can be represented by a human-engineered word sequence or by a learned continuous embedding. In…

While Pre-trained Language Models (PLMs) internalize a great amount of world knowledge, they have been shown incapable of recalling these knowledge to solve tasks requiring complex & multi-step reasoning. Similar to how humans develop a…

Intelligent agents such as robots are increasingly deployed in real-world, safety-critical settings. It is vital that these agents are able to explain the reasoning behind their decisions to human counterparts, however, their behavior is…

Intelligent agents such as robots are increasingly deployed in real-world, safety-critical settings. It is vital that these agents are able to explain the reasoning behind their decisions to human counterparts; however, their behavior is…

Language model-based instruction-following systems have lately shown increasing performance on many benchmark tasks, demonstrating the capability of adapting to a broad variety of instructions. However, such systems are often not designed…

The wayward quality of continuous prompts stresses the importance of their interpretability as unexpected and unpredictable behaviors appear following training, especially in the context of large language models automating people-sensitive…

Prompt tuning has achieved great success in transferring the knowledge from large pretrained vision-language models into downstream tasks, and has dominated the performance on visual grounding (VG). However, almost all existing prompt…

Current efficient fine-tuning methods (e.g., adapters, prefix-tuning, etc.) have optimized conditional text generation via training a small set of extra parameters of the neural language model, while freezing the rest for efficiency. While…

Systems now exist which are able to compile unification grammars into language models that can be included in a speech recognizer, but it is so far unclear whether non-trivial linguistically principled grammars can be used for this purpose.…

Providing examples is one of the most common way for end-users to interact with program synthesizers. However, program synthesis systems assume that examples consistent with the program are chosen at random, and do not exploit the fact that…

As applications of large language models (LLMs) become increasingly complex, the demand for robust complex instruction following capabilities is growing accordingly. We argue that a thorough understanding of the instruction itself,…

Current works in the generation of personalized dialogue primarily contribute to the agent presenting a consistent personality and driving a more informative response. However, we found that the generated responses from most previous models…

Automatic generation of paraphrases from a given sentence is an important yet challenging task in natural language processing (NLP), and plays a key role in a number of applications such as question answering, search, and dialogue. In this…