Related papers: When Models Decide and When They Bind: A Two-Stage…
This paper proposes CQ-VQA, a novel 2-level hierarchical but end-to-end model to solve the task of visual question answering (VQA). The first level of CQ-VQA, referred to as question categorizer (QC), classifies questions to reduce the…
Community Question Answering (CQA) has become a primary means for people to acquire knowledge, where people are free to ask questions or submit answers. To enhance the efficiency of the service, similar question identification becomes a…
Multilingual language models have shown decent performance in multilingual and cross-lingual natural language understanding tasks. However, the power of these multilingual models in code-switching tasks has not been fully explored. In this…
Multiple choice questions (MCQs) that can be generated from a domain ontology can significantly reduce human effort & time required for authoring & administering assessments in an e-Learning environment. Even though here are various methods…
As scientific knowledge grows at an unprecedented pace, evaluation benchmarks must evolve to reflect new discoveries and ensure language models are tested on current, diverse literature. We propose a scalable, modular framework for…
The widespread adoption of Large Language Models (LLMs) has become commonplace, particularly with the emergence of open-source models. More importantly, smaller models are well-suited for integration into consumer devices and are frequently…
When answering complex questions, people can seamlessly combine information from visual, textual and tabular sources. While interest in models that reason over multiple pieces of evidence has surged in recent years, there has been…
Multicriteria decision analysis (MCDA) is a widely used tool to support decisions in which a set of alternatives should be ranked or classified based on multiple criteria. Recent studies in MCDA have shown the relevance of considering not…
Human knowledge is collectively encoded in the roughly 6500 languages spoken around the world, but it is not distributed equally across languages. Hence, for information-seeking question answering (QA) systems to adequately serve speakers…
Effective abstention (EA), recognizing evidence insufficiency and refraining from answering, is critical for reliable multimodal systems. Yet existing evaluation paradigms for vision-language models (VLMs) and multi-agent systems (MAS)…
Large language models (LLMs) remain brittle on multi-hop question answering (MHQA), where answering requires combining evidence across documents through retrieval and reasoning. Iterative retrieval systems can fail by locking onto an early…
Large language models (LLMs) are increasingly used to generate multiple-choice questions (MCQs), where correct answers should ideally be uniformly distributed across options. However, we observe that LLMs exhibit systematic position biases…
We focus on Multimodal Machine Reading Comprehension (M3C) where a model is expected to answer questions based on given passage (or context), and the context and the questions can be in different modalities. Previous works such as RecipeQA…
Pre-training a model to learn transferable video-text representation for retrieval has attracted a lot of attention in recent years. Previous dominant works mainly adopt two separate encoders for efficient retrieval, but ignore local…
Recent literature shows that large-scale language modeling provides excellent reusable sentence representations with both recurrent and self-attentive architectures. However, there has been less clarity on the commonalities and differences…
Question Aware Open Information Extraction (Question aware Open IE) takes question and passage as inputs, outputting an answer tuple which contains a subject, a predicate, and one or more arguments. Each field of answer is a natural…
This paper describes our solution to the multi-modal learning challenge of ICML. This solution comprises constructing three-level representations in three consecutive stages and choosing correct tag words with a data-specific strategy.…
Video question answering has recently received a lot of attention from multimodal video researchers. Most video question answering datasets are usually in the form of multiple-choice. But, the model for the multiple-choice task does not…
As conventional answer selection (AS) methods generally match the question with each candidate answer independently, they suffer from the lack of matching information between the question and the candidate. To address this problem, we…
Continual Visual Question Answering (CVQA) based on pre-trained models(PTMs) has achieved promising progress by leveraging prompt tuning to enable continual multi-modal learning. However, most existing methods adopt cross-modal prompt…