Related papers: BiCon-Gate: Consistency-Gated De-colloquialisation…

In spoken question answering, QA systems are designed to answer questions from contiguous text spans within the related speech transcripts. However, the most natural way that human seek or test their knowledge is via human conversations.…

Conversational search utilizes muli-turn natural language contexts to retrieve relevant passages. Existing conversational dense retrieval models mostly view a conversation as a fixed sequence of questions and responses, overlooking the…

Large Language Models have significantly advanced natural language processing tasks, but remain prone to generating incorrect or misleading but plausible arguments. This issue, known as hallucination, is particularly concerning in…

Fact-checking requires retrieving evidence related to a claim under investigation. The task can be formulated as question generation based on a claim, followed by question answering. However, recent question generation approaches assume…

Language models are increasingly being used in important decision pipelines, so ensuring the correctness of their outputs is crucial. Recent work has proposed evaluating the "factuality" of claims decomposed from a language model generation…

Existing benchmarks treat multi-turn conversation and reasoning-intensive retrieval separately, yet real-world information seeking requires both. To bridge this gap, we present a benchmark for reasoning-based conversational information…

While dialogue remains an important end-goal of natural language research, the difficulty of evaluation is an oft-quoted reason why it remains troublesome to make real progress towards its solution. Evaluation difficulties are actually…

Retrieval-Augmented Generation (RAG) has become a powerful paradigm for enhancing large language models (LLMs) through external knowledge retrieval. Despite its widespread attention, existing academic research predominantly focuses on…

Large language models (LLMs) can effectively elicit human preferences through multi-turn dialogue. Complex tasks can be accomplished through iterative clarifying questions and final responses generated by an LLM acting as a questioner…

Self-consistency-based approaches, which involve repeatedly sampling multiple outputs and selecting the most consistent one as the final response, prove to be remarkably effective in improving the factual accuracy of large language models.…

Conversational search seeks to retrieve relevant passages for the given questions in conversational question answering. Conversational Query Reformulation (CQR) improves conversational search by refining the original queries into…

Simultaneous Speech-to-Text translation serves a critical role in real-time crosslingual communication. Despite the advancements in recent years, challenges remain in achieving stability in the translation process, a concern primarily…

Automated fact-checking has drawn considerable attention over the past few decades due to the increase in the diffusion of misinformation on online platforms. This is often carried out as a sequence of tasks comprising (i) the detection of…

Claim normalization is an integral part of any automatic fact-check verification system. It parses the typically noisy claim data, such as social media posts into normalized claims, which are then fed into downstream veracity classification…

The proliferation of misinformation in digital platforms reveals the limitations of traditional detection methods, which mostly rely on static classification and fail to capture the intricate process of real-world fact-checking. Despite…

Automated evidence-based misinformation detection systems, which evaluate the veracity of short claims against evidence, lack comprehensive analysis of their adversarial vulnerabilities. Existing black-box text-based adversarial attacks are…

Conversational Question Answering (CQA) aims to answer questions contained within dialogues, which are not easily interpretable without context. Developing a model to rewrite conversational questions into self-contained ones is an emerging…

Distilling multi-step reasoning abilities from large language models (LLMs) into compact student models remains challenging due to noisy rationales, hallucinated supervision, and static teacher-student interactions. Existing reasoning…

Complex claim fact-checking performs a crucial role in disinformation detection. However, existing fact-checking methods struggle with claim vagueness, specifically in effectively handling latent information and complex relations within…

Improving the quality of model-generated summaries, especially factuality, the accuracy of a summary with respect to its source content, remains a challenge. While reranking could select the optimal output from multiple generated…