相关论文: Pointwise Mutual Information Based Metric and Deco…

Because high-quality data is like oxygen for AI systems, effectively eliciting information from crowdsourcing workers has become a first-order problem for developing high-performance machine learning algorithms. Two prevalent paradigms,…

Knowledge-grounded dialogue systems powered by large language models often generate responses that, while fluent, are not attributable to a relevant source of information. Progress towards models that do not exhibit this issue requires…

Automated fact-checking has been a challenging task for the research community. Prior work has explored various strategies, such as end-to-end training, retrieval-augmented generation, and prompt engineering, to build robust fact-checking…

Recent advances in automatic evaluation metrics for text have shown that deep contextualized word representations, such as those generated by BERT encoders, are helpful for designing metrics that correlate well with human judgements. At the…

Matching for causal inference is a well-studied problem, but standard methods fail when the units to match are text documents: the high-dimensional and rich nature of the data renders exact matching infeasible, causes propensity scores to…

Text-to-image generative models excel in creating images from text but struggle with ensuring alignment and consistency between outputs and prompts. This paper introduces TextMatch, a novel framework that leverages multimodal optimization…

Understanding dependencies between variables is critical for interpretability and efficient generation in masked diffusion models (MDMs), yet these models primarily expose marginal conditional distributions and do not explicitly represent…

Research shows that dialogue, the interactive process through which participants articulate their thinking, plays a central role in constructing shared understanding, coordinating action, and shaping learning outcomes in teams. Analysing…

Qualitative relationships describe how increasing or decreasing one property (e.g. altitude) affects another (e.g. temperature). They are an important aspect of natural language question answering and are crucial for building chatbots or…

Generative search engines and deep research LLM agents promise trustworthy, source-grounded synthesis, yet users regularly encounter overconfidence, weak sourcing, and confusing citation practices. We introduce DeepTRACE, a novel…

This work focuses on learning useful and robust deep world models using multiple, possibly unreliable, sensors. We find that current methods do not sufficiently encourage a shared representation between modalities; this can cause poor…

The degree of success in document summarization processes depends on the performance of the method used in identifying significant sentences in the documents. The collection of unique words characterizes the major signature of the document,…

Despite their impressive capabilities, diffusion-based text-to-image (T2I) models can lack faithfulness to the text prompt, where generated images may not contain all the mentioned objects, attributes or relations. To alleviate these…

Chain-of-thought (CoT) prompting is widely used as a reasoning aid and is often treated as a transparency mechanism. Yet behavioral gains under CoT do not imply that the model's internal computation causally depends on the emitted reasoning…

Most prompt-optimization methods refine a single static template, making them ineffective in complex and dynamic user scenarios. Existing query-dependent approaches rely on unstable textual feedback or black-box reward models, providing…

Gas chromatography-mass spectrometry (GC-MS) is a widely used analytical method for chemical substance detection, but measurement reliability tends to deteriorate in the presence of interfering substances. In particular, interfering…

Despite the growing development of long-context large language models (LLMs), data-centric approaches relying on synthetic data have been hindered by issues related to faithfulness, which limit their effectiveness in enhancing model…

Factuality is a crucial requirement in information seeking dialogue: the system should respond to the user's queries so that the responses are meaningful and aligned with the knowledge provided to the system. However, most modern large…

Recent advancements in large language models (LLMs) have shown promise in generating psychotherapeutic dialogues, particularly in the context of motivational interviewing (MI). However, the inherent lack of transparency in LLM outputs…

Large language models (LLMs) are increasingly capable and prevalent, and can be used to produce creative content. The quality of content is influenced by the prompt used, with more specific prompts that incorporate examples generally…