· ai
[Paper] How to Correctly Report LLM-as-a-Judge Evaluations
Large language models (LLMs) are increasingly used as evaluators in lieu of humans. While scalable, their judgments are noisy due to imperfect specificity and s...
-
- · ai
[Paper] MortgageLLM: Domain-Adaptive Pretraining with Residual Instruction Transfer, Alignment Tuning, and Task-Specific Routing
Large Language Models (LLMs) demonstrate exceptional capabilities across general domains, yet their application to specialized sectors such as mortgage finance ...
- · ai
[Paper] ASR Error Correction in Low-Resource Burmese with Alignment-Enhanced Transformers using Phonetic Features
This paper investigates sequence-to-sequence Transformer models for automatic speech recognition (ASR) error correction in low-resource Burmese, focusing on dif...
- · ai
[Paper] Orthographic Constraint Satisfaction and Human Difficulty Alignment in Large Language Models
Large language models must satisfy hard orthographic constraints during controlled text generation, yet systematic cross-architecture evaluation remains limited...
- · ai
[Paper] Enhancing Burmese News Classification with Kolmogorov-Arnold Network Head Fine-tuning
In low-resource languages like Burmese, classification tasks often fine-tune only the final classification layer, keeping pre-trained encoder weights frozen. Wh...
- · ai
[Paper] Context-Aware Pragmatic Metacognitive Prompting for Sarcasm Detection
Detecting sarcasm remains a challenging task in the areas of Natural Language Processing (NLP) despite recent advances in neural network approaches. Currently, ...
- · ai
[Paper] Zipf Distributions from Two-Stage Symbolic Processes: Stability Under Stochastic Lexical Filtering
Zipf's law in language lacks a definitive origin, debated across fields. This study explains Zipf-like behavior using geometric mechanisms without linguistic el...
- · ai
[Paper] A Unified Understanding of Offline Data Selection and Online Self-refining Generation for Post-training LLMs
Offline data selection and online self-refining generation, which enhance the data quality, are crucial steps in adapting large language models (LLMs) to specif...
- · ai
[Paper] Semantic Anchors in In-Context Learning: Why Small LLMs Cannot Flip Their Labels
Can in-context learning (ICL) override pre-trained label semantics, or does it merely refine an existing semantic backbone? We address this question by treating...
- · ai
[Paper] Gated KalmaNet: A Fading Memory Layer Through Test-Time Ridge Regression
As efficient alternatives to softmax Attention, linear state-space models (SSMs) achieve constant memory and linear compute, but maintain only a lossy, fading s...
- · ai
[Paper] TrackList: Tracing Back Query Linguistic Diversity for Head and Tail Knowledge in Open Large Language Models
Large Language Models (LLMs) have proven efficient in giving definition-type answers to user input queries. While for humans giving various types of answers, su...
- · ai
[Paper] Even with AI, Bijection Discovery is Still Hard: The Opportunities and Challenges of OpenEvolve for Novel Bijection Construction
Evolutionary program synthesis systems such as AlphaEvolve, OpenEvolve, and ShinkaEvolve offer a new approach to AI-assisted mathematical discovery. These syste...