相关论文: Knowledge Dependency Estimation for Reliable Quest…

Language models often benefit from external knowledge beyond parametric knowledge. While this combination enhances performance, achieving reliable knowledge utilization remains challenging, as it requires assessing the state of each…

The robustness to distribution changes ensures that NLP models can be successfully applied in the realistic world, especially for information extraction tasks. However, most prior evaluation benchmarks have been devoted to validating…

Supervised fine-tuning (SFT) is a common approach to improve the domain-specific question-answering (QA) performance of large language models (LLMs). However, recent literature reveals that due to the conflicts between LLMs' internal…

Requirements are inherently interconnected through various types of dependencies. Identifying these dependencies is essential, as they underpin critical decisions and influence a range of activities throughout software development. However,…

Editing Large language models (LLMs) with real-world, unstructured knowledge is essential for correcting and updating their internal parametric knowledge. In this work, we revisit the fundamental next-token prediction (NTP) as a candidate…

Knowledge tracing (KT) aims to estimate a student's evolving knowledge state and predict their performance on new exercises based on performance history. Many realistic classroom settings for KT are typically low-resource in data and…

LLM evaluation benchmarks have traditionally separated the testing of knowledge/reasoning capabilities from instruction following. In this work, we study the interaction between knowledge and instruction following, and observe that LLMs…

Large Language Models (LLMs) have been increasingly studied as neural knowledge bases for supporting knowledge-intensive applications such as question answering and fact checking. However, the structural organization of their knowledge…

Open book question answering is a type of natural language based QA (NLQA) where questions are expected to be answered with respect to a given set of open book facts, and common knowledge about a topic. Recently a challenge involving such…

Benchmarks play a crucial role in tracking the rapid advancement of large language models (LLMs) and identifying their capability boundaries. However, existing benchmarks predominantly curate questions at the question level, suffering from…

Retriever-augmented instruction-following models are attractive alternatives to fine-tuned approaches for information-seeking tasks such as question answering (QA). By simply prepending retrieved documents in its input along with an…

Retrieval augmented Question Answering (QA) helps QA models overcome knowledge gaps by incorporating retrieved evidence, typically a set of passages, alongside the question at test time. Previous studies show that this approach improves QA…

The ability of knowledge graphs to represent complex relationships at scale has led to their adoption for various needs including knowledge representation, question-answering, and recommendation systems. Knowledge graphs are often…

How do large language models (LLMs) know what they know? Answering this question has been difficult because pre-training data is often a "black box" - unknown or inaccessible. The recent release of nanochat - a family of small LLMs with…

In this work, we take a closer look at the evaluation of two families of methods for enriching information from knowledge graphs: Link Prediction and Entity Alignment. In the current experimental setting, multiple different scores are…

Programming Knowledge Tracing (PKT) has recently advanced through hybrid approaches that integrate attention-based feature modeling for code representation with RNN-based sequential prediction. While these models report strong empirical…

The dependency between an adequate question formulation and correct answer selection is a very intriguing but still underexplored area. In this paper, we show that question rewriting (QR) of the conversational context allows to shed more…

Large language models (LLMs) achieve strong reasoning performance through chain-of-thought (CoT) reasoning, yet often generate unnecessarily long reasoning paths that incur high inference cost. Recent self-consistency-based approaches…

With the rapid growth of knowledge bases (KBs), question answering over knowledge base, a.k.a. KBQA has drawn huge attention in recent years. Most of the existing KBQA methods follow so called encoder-compare framework. They map the…

Large Language Models (LLMs) perform well in general QA but often struggle in domain-specific scenarios. Retrieval-Augmented Generation (RAG) introduces external knowledge but suffers from hallucinations and latency due to noisy retrievals.…