FormulaQA: A Question Answering Dataset for Formula-Based Numerical Reasoning

The application of formulas is a fundamental ability of humans when addressing numerical reasoning problems. However, existing numerical reasoning datasets seldom explicitly indicate the formulas employed during the reasoning steps. To bridge this gap, we propose a question answering dataset for formula-based numerical reasoning called FormulaQA, from junior high school physics examinations. We further conduct evaluations on LLMs with size ranging from 7B to over 100B parameters utilizing zero-shot and few-shot chain-of-thoughts methods and we explored the approach of using retrieval-augmented LLMs when providing an external formula database. We also fine-tune on smaller models with size not exceeding 2B. Our empirical findings underscore the significant potential for improvement in existing models when applied to our complex, formula-driven FormulaQA.

Furthest Reasoning with Plan Assessment: Stable Reasoning Path with Retrieval-Augmented Large Language Models

Large Language Models (LLMs), acting as a powerful reasoner and generator, exhibit extraordinary performance across various natural language tasks, such as question answering (QA). Among these tasks, Multi-Hop Question Answering (MHQA) stands as a widely discussed category, necessitating seamless integration between LLMs and the retrieval of external knowledge. Existing methods employ LLM to generate reasoning paths and plans, and utilize IR to iteratively retrieve related knowledge, but these approaches have inherent flaws. On one hand, Information Retriever (IR) is hindered by the low quality of generated queries by LLM. On the other hand, LLM is easily misguided by the irrelevant knowledge by IR. These inaccuracies, accumulated by the iterative interaction between IR and LLM, lead to a disaster in effectiveness at the end. To overcome above barriers, in this paper, we propose a novel pipeline for MHQA called Furthest-Reasoning-with-Plan-Assessment (FuRePA), including an improved framework (Furthest Reasoning) and an attached module (Plan Assessor). 1) Furthest reasoning operates by masking previous reasoning path and generated queries for LLM, encouraging LLM generating chain of thought from scratch in each iteration. This approach enables LLM to break the shackle built by previous misleading thoughts and queries (if any). 2) The Plan Assessor is a trained evaluator that selects an appropriate plan from a group of candidate plans proposed by LLM. Our methods are evaluated on three highly recognized public multi-hop question answering datasets and outperform state-of-the-art on most metrics (achieving a 10%-12% in answer accuracy).

DyRRen: A Dynamic Retriever-Reranker-Generator Model for Numerical Reasoning over Tabular and Textual Data

Numerical reasoning over hybrid data containing tables and long texts has recently received research attention from the AI community. To generate an executable reasoning program consisting of math and table operations to answer a question, state-of-the-art methods use a retriever-generator pipeline. However, their retrieval results are static, while different generation steps may rely on different sentences. To attend to the retrieved information that is relevant to each generation step, in this paper, we propose DyRRen, an extended retriever-reranker-generator framework where each generation step is enhanced by a dynamic reranking of retrieved sentences. It outperforms existing baselines on the FinQA dataset.

From Node Interaction to Hop Interaction: New Effective and Scalable Graph Learning Paradigm

Existing Graph Neural Networks (GNNs) follow the message-passing mechanism that conducts information interaction among nodes iteratively. While considerable progress has been made, such node interaction paradigms still have the following limitation. First, the scalability limitation precludes the wide application of GNNs in large-scale industrial settings since the node interaction among rapidly expanding neighbors incurs high computation and memory costs. Second, the over-smoothing problem restricts the discrimination ability of nodes, i.e., node representations of different classes will converge to indistinguishable after repeated node interactions. In this work, we propose a novel hop interaction paradigm to address these limitations simultaneously. The core idea of hop interaction is to convert the target of message-passing from nodes into multi-hop features inside each node. Specifically, it first pre-computed multi-hop features of nodes to reduce computation costs during training and inference. Then, it conducts a non-linear interaction among multi-hop features to enhance the discrimination of nodes. We design a simple yet effective HopGNN framework that can easily utilize existing GNNs to achieve hop interaction. Furthermore, we propose a multi-task learning strategy with a self-supervised learning objective to enhance HopGNN. We conduct extensive experiments on 12 benchmark datasets in a wide range of domains, scales, and smoothness of graphs. Experimental results show that our methods achieve superior performance while maintaining high scalability and efficiency.

Binaural Rendering of Ambisonic Signals by Neural Networks

Binaural rendering of ambisonic signals is of broad interest to virtual reality and immersive media. Conventional methods often require manually measured Head-Related Transfer Functions (HRTFs). To address this issue, we collect a paired ambisonic-binaural dataset and propose a deep learning framework in an end-to-end manner. Experimental results show that neural networks outperform the conventional method in objective metrics and achieve comparable subjective metrics. To validate the proposed framework, we experimentally explore different settings of the input features, model structures, output features, and loss functions. Our proposed system achieves an SDR of 7.32 and MOSs of 3.83, 3.58, 3.87, 3.58 in quality, timbre, localization, and immersion dimensions.

Inferring Taxi Status Using GPS Trajectories

In this paper, we infer the statuses of a taxi, consisting of occupied, non-occupied and parked, in terms of its GPS trajectory. The status information can enable urban computing for improving a city's transportation systems and land use planning. In our solution, we first identify and extract a set of effective features incorporating the knowledge of a single trajectory, historical trajectories and geographic data like road network. Second, a parking status detection algorithm is devised to find parking places (from a given trajectory), dividing a trajectory into segments (i.e., sub-trajectories). Third, we propose a two-phase inference model to learn the status (occupied or non-occupied) of each point from a taxi segment. This model first uses the identified features to train a local probabilistic classifier and then carries out a Hidden Semi-Markov Model (HSMM) for globally considering long term travel patterns. We evaluated our method with a large-scale real-world trajectory dataset generated by 600 taxis, showing the advantages of our method over baselines.