Related papers: QADYNAMICS: Training Dynamics-Driven Synthetic QA …
We investigate the robustness of reasoning models trained for step-by-step problem solving by introducing query-agnostic adversarial triggers - short, irrelevant text that, when appended to math problems, systematically mislead models to…
Commonsense Knowledge Bases (CSKB) Population, which aims at automatically expanding knowledge in CSKBs with external resources, is an important yet hard task in NLP. Fang et al. (2021a) proposed a CSKB Population (CKBP) framework with an…
Complex question-answering (CQA) involves answering complex natural-language questions on a knowledge base (KB). However, the conventional neural program induction (NPI) approach exhibits uneven performance when the questions have different…
Search typically relies on keyword queries, but these are often semantically ambiguous. We propose to overcome this by offering users natural language questions, based on their keyword queries, to disambiguate their intent. This…
Language Models (LMs) have revolutionized natural language processing, enabling high-quality text generation through prompting and in-context learning. However, models often struggle with long-context summarization due to positional biases,…
Fine-tuning for large language models (LLMs) typically requires substantial amounts of high-quality supervised data, which is both costly and labor-intensive to acquire. While synthetic data generation has emerged as a promising solution,…
Reasoning over Commonsense Knowledge Bases (CSKB), i.e. CSKB reasoning, has been explored as a way to acquire new commonsense knowledge based on reference knowledge in the original CSKBs and external prior knowledge. Despite the advancement…
Automatic dialogue coherence evaluation has attracted increasing attention and is crucial for developing promising dialogue systems. However, existing metrics have two major limitations: (a) they are mostly trained in a simplified two-level…
Confusing-words are commonly encountered in real-life keyword spotting applications, which causes severe degradation of performance due to complex spoken terms and various kinds of words that sound similar to the predefined keywords. To…
Synthesizing safety controllers for general nonlinear systems is a highly challenging task, particularly when the system models are unknown, and input constraints are present. While some recent efforts have explored data-driven safety…
Existing NLP datasets contain various biases that models can easily exploit to achieve high performances on the corresponding evaluation sets. However, focusing on dataset-specific biases limits their ability to learn more generalizable…
Naturally situated conversations encapsulate the social norms inherent to their context, reflecting both the relationships between interlocutors and the underlying communicative intent. In this paper, we propose a novel, multi-step…
AI-based persona simulation -- often referred to as digital twin simulation -- is increasingly used for market research, recommender systems, and social sciences. Despite their flexibility, large language models (LLMs) often exhibit…
If a question cannot be answered with the available information, robust systems for question answering (QA) should know _not_ to answer. One way to build QA models that do this is with additional training data comprised of unanswerable…
Current deep learning models are not designed to simultaneously address three fundamental questions: predict class labels to solve a given classification task (the "What?"), simulate changes in the situation to evaluate how this impacts…
Zero-shot transfer learning for multi-domain dialogue state tracking can allow us to handle new domains without incurring the high cost of data acquisition. This paper proposes new zero-short transfer learning technique for dialogue state…
Intelligent Traffic Monitoring (ITMo) technologies hold the potential for improving road safety/security and for enabling smart city infrastructure. Understanding traffic situations requires a complex fusion of perceptual information with…
Question Answering (QA) systems require a large amount of annotated data which is costly and time-consuming to gather. Converting datasets of existing QA benchmarks are challenging due to different formats and complexities. To address these…
Knowledge Base Completion (KBC) has been a very active area lately. Several recent KBCpapers propose architectural changes, new training methods, or even new formulations. KBC systems are usually evaluated on standard benchmark datasets:…
We introduce Jamendo-QA, a large-scale dataset for Music Question Answering (Music-QA). The dataset is built on freely licensed tracks from the Jamendo platform and is automatically annotated using the Qwen-Omni model. Jamendo-QA provides…