Related papers: eTracer: Towards Traceable Text Generation via Cla…
Reliable mathematical and scientific reasoning remains an open challenge for large vision-language models. Standard final-answer evaluation often masks reasoning errors, allowing silent failures to persist. To address this gap, we introduce…
Despite rapid progress, pretrained vision-language models still struggle when answers depend on tiny visual details or on combining clues spread across multiple regions, as in documents and compositional queries. We address this by framing…
A retriever, which retrieves relevant knowledge pieces from a knowledge base given a context, is an important component in many natural language processing (NLP) tasks. Retrievers have been introduced in knowledge-grounded dialog systems to…
Empathetic response generation is a crucial task for creating more human-like and supportive conversational agents. However, existing methods face a core trade-off between the analytical depth of specialized models and the generative…
In this paper we present a data-driven, integrated approach to speaker verification, which maps a test utterance and a few reference utterances directly to a single score for verification and jointly optimizes the system's components using…
We argue that trustworthy AI agents, especially in high-stakes and policy-governed domains, should make execution conditional on certified traces rather than rely only on stronger generative models, output-level guardrails, or post-hoc…
Long context large language models (LLMs) are deployed in many real-world applications such as RAG, agent, and broad LLM-integrated applications. Given an instruction and a long context (e.g., documents, PDF files, webpages), a long context…
Voice conversion (VC), as a voice style transfer technology, is becoming increasingly prevalent while raising serious concerns about its illegal use. Proactively tracing the origins of VC-generated speeches, i.e., speaker traceability, can…
Eligibility criteria (EC) are essential for clinical trial design, yet drafting them remains a time-intensive and cognitively demanding task for clinicians. Existing automated approaches often fall at two extremes either requiring highly…
LLMs are vulnerable to hallucinations, and thus their outputs generally require laborious human verification for high-stakes applications. To this end, we propose symbolically grounded generation (SymGen) as a simple approach for enabling…
Research on AI-generated text detection has presented a number of approaches to discern human from AI prose, some of which achieving high in-distribution performance. However, real-world applicability has stalled because their outputs are…
Question answering (QA) over structured tables requires not only accurate answers but also transparency about which cells support them. Existing table QA systems rarely provide fine-grained attribution, so even correct answers often lack…
Query-document relevance prediction is a critical problem in Information Retrieval systems. This problem has increasingly been tackled using (pretrained) transformer-based models which are finetuned using large collections of labeled data.…
Document grounded generation is the task of using the information provided in a document to improve text generation. This work focuses on two different document grounded generation tasks: Wikipedia Update Generation task and Dialogue…
Current captioning approaches can describe images using black-box architectures whose behavior is hardly controllable and explainable from the exterior. As an image can be described in infinite ways depending on the goal and the context at…
A growing body of work studies how to answer a question or verify a claim by generating a natural language "proof": a chain of deductive inferences yielding the answer based on a set of premises. However, these methods can only make sound…
Joint video-language learning has received increasing attention in recent years. However, existing works mainly focus on single or multiple trimmed video clips (events), which makes human-annotated event boundaries necessary during…
A plausible future mathematical claim must satisfy two constraints: it should follow the direction of prior work and respect the formal dependencies that constrain what can validly follow. Existing approaches typically model only one of…
Conducting experiments and documenting results is daily business of scientists. Good and traceable documentation enables other scientists to confirm procedures and results for increased credibility. Documentation and scientific conduct are…
Verifying the veracity of claims requires reasoning over a large knowledge base, often in the form of corpora of trustworthy sources. A common approach consists in retrieving short portions of relevant text from the reference documents and…