Related papers: Verifiable Generation with Subsentence-Level Fine-…

Language models (LMs) may lead their users to make suboptimal downstream decisions when they confidently hallucinate. This issue can be mitigated by having the LM verbally convey the probability that its claims are correct, but existing…

Multimodal Large Language Models (MLLMs) have advanced in integrating diverse modalities but frequently suffer from hallucination. A promising solution to mitigate this issue is to generate text with citations, providing a transparent chain…

Retrieval-Augmented Generation (RAG) grounds Large Language Models (LLMs) in external knowledge but often suffers from flat context representations and stateless retrieval, leading to unstable performance. We propose Stateful…

Language models (LMs) have revolutionized the way we interact with information, but they often generate nonfactual text, raising concerns about their reliability. Previous methods use external knowledge as references for text generation to…

Large Language Models (LLMs) are accelerating scientific idea generation, but rigorously evaluating these numerous, often superficial, AI-generated propositions for novelty and factual accuracy is a critical bottleneck; manual verification…

Recently, a plethora of works have proposed inference-time algorithms (e.g. best-of-n), which incorporate verifiers to assist the generation process. Their quality-efficiency trade-offs have been empirically benchmarked on a variety of…

Current disfluency detection methods heavily rely on costly and scarce human-annotated data. To tackle this issue, some approaches employ heuristic or statistical features to generate disfluent sentences, partially improving detection…

Visual Language Models (VLMs) are powerful generative tools but often produce factually inaccurate outputs due to a lack of robust reasoning capabilities. While extensive research has been conducted on integrating external knowledge for…

Paraphrase generation is a longstanding NLP task that has diverse applications for downstream NLP tasks. However, the effectiveness of existing efforts predominantly relies on large amounts of golden labeled data. Though unsupervised…

Improving context faithfulness in large language models is essential for developing trustworthy retrieval augmented generation systems and mitigating hallucinations, especially in long-form question answering (LFQA) tasks or scenarios…

Large Language Models (LLM) are increasingly trained on data generated by other LLM, either because generated text and images become part of the pre-training corpus, or because synthetized data is used as a replacement for expensive…

Generating with citations is crucial for trustworthy Large Language Models (LLMs), yet even advanced LLMs often produce mismatched or irrelevant citations. Existing methods over-optimize citation fidelity while overlooking relevance to the…

The ability to reason with natural language is a fundamental prerequisite for many NLP tasks such as information extraction, machine translation and question answering. To quantify this ability, systems are commonly tested whether they can…

Justification is an explanation that supports the veracity assigned to a claim in fact-checking. However, the task of justification generation is previously oversimplified as summarization of fact-check article authored by fact-checkers.…

In the rapidly evolving field of text generation, the demand for more precise control mechanisms has become increasingly apparent. To address this need, we present a novel methodology, LIFI, which offers a lightweight approach with…

Generative Artificial Intelligence (GenAI) has demonstrated its capabilities in the present world that reduce human effort significantly. It utilizes deep learning techniques to create original and realistic content in terms of text,…

The emergence of prompting as the dominant paradigm for leveraging Large Language Models (LLMs) has led to a proliferation of LLM-native software, where application behavior arises from complex, stochastic data transformations. However, the…

We present an empirical study of groundedness in long-form question answering (LFQA) by retrieval-augmented large language models (LLMs). In particular, we evaluate whether every generated sentence is grounded in the retrieved documents or…

Evaluating the factuality of long-form generations from Large Language Models (LLMs) remains challenging due to efficiency bottlenecks and reliability concerns. Prior efforts attempt this by decomposing text into claims, searching for…

Recent work has shown that Large Language Models (LLMs) are not only a suitable tool for code generation but also capable of generating annotation-based code specifications. Scaling these methodologies may allow us to deduce provable…