Self-Assessment Reinforcement Learning (SARL), a reinforcement learning framework in which models learn to recognize their own search state during training and improve their search behavior accordingly, without requiring additional assessment at test time, outperforms methods built on auxiliary supervision or multi-age...
Taewhoo Lee, Min-Ju Song, Jungwoo Park et al.· 0 citations
LLM-based chat agents are increasingly used for complex, multi-turn, multilingual medical triage in low- and middle-income countries (LMICs), yet evaluation methods focus on single-turn, English-only benchmarks that primarily test the chatbots' knowledge. In practice, users are often confused, overwhelmed, or emotional...
Deepali Mittal, Dheeraj Mundhra, Yulia Sidorova et al.· 0 citations
MemPlan is proposed, a memory-conditioned PDDL planning framework for partially observable interactive text environments, which improves task completion and step efficiency over language-only and PDDL-aware baselines, while substantially reducing online token cost compared with LLM-planning baselines such as ReAct.
The massively multilingual translation systems that now include Sicilian learned it from noisy, non-standardised web text. To obtain better translation quality, we redevelop the small neural machine translation (NMT) system that Wdowiak customized for Sicilian. We rebuild on maintained software the extraction of the pa...
Donato Meoli, Eryk Wdowiak· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Hallucinated citations make it harder to trace sources and verify the evidence behind scientific claims. Detecting them is difficult because bibliographic records can be incomplete or differ across source types and publication versions. A plausible match alone neither validates the citation nor establishes its underlyi...
Large Language Models (LLMs) have accelerated research on low-resource and multilingual NLP, but their effectiveness in creating an equitable landscape remains unmapped. We analyze 1,158 peer-reviewed open-access papers published between 2020 and 2025, examining research attention to low-resource languages (LRLs) and r...
Model fusion aims to integrate the capabilities of multi-expert models into a single model. Existing evaluations offer limited coverage of reasoning with long chains of thought and tool use, while strong average performance can mask substantial losses in individual expert capabilities. We introduce FusionEval, a benchm...
Shuo Cai, Yang-Gan Gu, Yuhang Liu et al.· 0 citations
Many Indian banks serve customers through FAQ pages and scripted chatbots. Assistants based on language models could respond faster and carry out requests such as blocking a card, but only if they give correct information and follow the bank's rules. These rules prescribe a procedure, a set of required steps, such as o...
This work presents the first digital assistant named Lighthouse, the first digital assistant named Lighthouse--commonly called a chatbot--for exploring the Civil Rights period of the United States using data from South Carolina.
John A. Aydin, Angela Williams, Steven Dindl et al.· 0 citations
Zero-shot cross-lingual voice cloning often carries the reference speaker's accent into the target language. We propose closed-loop dual-reference guidance, which pairs the original reference with a reusable native anchor constructed by voice conversion (VC). The references initialize separate language-model (LM) state...
Yuan-Zhong Zheng, Wei Huang, Min-Hua Ma et al.· 0 citations
This work asks how consulting memory during dialogue changes what users go on to say, and thus what the memory comes to reveal, and across four support models, memory raises response quality but also empirical leakage, the share of attribute values correctly inferred from the record, by a margin that widens over sessio...
Across three visual tasks, it is shown that pathway selection is task-dependent, and that data distribution and prompt design can also modulate which pathway is used to solve the image-based query.
Israfel Salazar, Stella Frank, Dan Oneata et al.· arXiv.org· 3 citations· ⚡1
Flint-interactive gives AI agents a language for creating interactive visualizations. Click a chart, filter data, highlight related content, and explore beyond the view the author originally chose. The post Flint-interactive: A language for creating interactive data visualizations appeared first on Microsoft Research.
