Large language models (LLMs) are increasingly used to simulate human survey responses and behavioral reactions, yet unreliable simulations can mislead social science conclusions. However, existing evaluations focus on end-to-end scores, leaving it unclear how different aspects of the simulation process interact to dete...
Pei-Wen Wang, Lei Wang, Yuan-Zi Li et al.· Proceedings of the 2026 Conf...· 0 citations
ChainDoRA is proposed, a weight-decomposed adaptation framework that constructs the directional low-rank factors from a connected Tensor-Train (TT) chain, where the adapter rank forms the boundary rank between input- and output-side TT contractions and an independent TT rank controls representation capacity and paramet...
Ashfak Yeafi, M. Hasan, Md Khairul Islam· 0 citations
A feedback-based word deduction framework based on the Jotto problem is proposed, and the problem space is represented as a weighted graph where all valid words correspond to nodes, and the edge weight is defined by the number of common letters between the two words. Finally, the gameplay is defined as an iterative con...
The results show that the strongest systems move beyond single-pass prompting and instead rely on structured evidence extraction, retrieval, verification, and orchestration across multiple components.
Artemis Llabrés, Marc Serra Ortega, Tomàs Ockier et al.· Lecture Notes in Computer Sc...· 1 citation
Reach audiences
Advertise in front of researchers, engineers, and readers.
For a long-horizon LLM agent, the memory question is not what was once recorded but what \emph{currently holds}. Most designs answer it only indirectly: every interaction is stored, and the present is reconstructed at query time by retrieving and reconciling records, so stale values re-enter and the same conflicts are...
The results demonstrate the importance of retrieval-centered verification and claim decomposition, while highlighting the challenges posed by ambiguous and interpretive reviewer claims.
Alireza Daghighfarsoodeh, Sajad Ebrahimi, A. Ghorbanpour et al.· 0 citations
Under one concise prompt and reference-overlap scorer, a released 406M specialist exceeds five proprietary hosted models by at least 6.2 ROUGE-1, but output length and absent human or factuality evaluation limit this ordering.
This paper tests whether the paradigm transfers to Sanskrit, an ancient, low-resource language whose phonological fusion (sandhi), morphological inflection, compounding, and polysemy pose a unique challenge.
A measured failure taxonomy of the two leading Rust ML frameworks, Candle and Burn, as training (not inference) backends in 2026 is considered: the more useful contribution is a measured failure taxonomy of the two leading Rust ML frameworks, Candle and Burn, as training (not inference) backends in 2026.
VeriSoftBench is introduced, a benchmark of 500 Lean 4 proof obligations drawn from open-source formal-methods developments and packaged to preserve realistic repository context and cross-file dependencies and results show that success is strongly correlated with transitive repository dependence.
Adapting large language model (LLM)-based automatic speech recognition (ASR) systems to new domains using text-only data is a significant yet underexplored challenge. Standard fine-tuning of the LLM on the target domain text often disrupts the critical alignment between the speech and text modality learned by the proje...
Andr\'es Carofilis, Sergio Burdisso, Esa\'u Villatoro-Tello et al.· 0 citations
Attention Residuals (AttnRes) replace the fixed residual sum with depth-wise attention over previous sub-layer outputs in Large Language Models (LLMs), but use each output as both a full-dimensional key and value. This couples routing with representation and makes the cost of computing depth-routing scores scale with h...
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.
