Names are personal identifiers, but they also carry social meaning and are widely used to evaluate how language models treat different people. Such evaluations typically assume that matched names are comparable model inputs. We show that this assumption often fails at the lexical interface: matched names are not necess...
Large language models (LLMs) perform table-centric prediction through in-context learning, making demonstration selection critical to performance. Existing retrieval methods prioritize similarity to the query, but similar demonstrations often reinforce the model's likely prediction rather than reveal the distinctions n...
Soroush Omidvartehrani, Mohammadamin Habibollah, Mohammadreza Daviran et al.· 0 citations
Automatic scientific survey generation has become an important task in scientific document processing. The common approach of retrieving literature from a single source (e.g., arXiv) and generating surveys through a one-pass large language model (LLM) call often leads to limited reference coverage and, more importantly...
Tong Bao, Mir Tafseer Nayeem, Yi Zhao et al.· Knowledge-Based Systems· 0 citations
PARTAB (Partition-Aware Reasoning overTables), a framework that constructs a structured evidence interface between the LLM and the table, demonstrates the value of structured, partition aware evidence construction for scalable table reasoning.
PRISM, an agentic retrieval framework that leverages large language models in a structured loop to retrieve relevant evidence with high precision and recall, achieves higher retrieval accuracy while filtering out distracting content, enabling downstream QA models to surpass full-context answer accuracy while relying on...
Md Mahadi Hasan Nahid, Davood Rafiei· arXiv.org· 8 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
