- CricBench: A Multilingual Benchmark for Evaluating LLMs in Cricket Analytics
Vaibhav Devraj, Dhruv Kumar, Jagat Sesh Challa, Parth Agarwal, Navya Kommuri · Dec 26, 2025
Expert Verification
To investigate this potential capability gap, we present CricBench, a comprehensive benchmark suite for evaluating LLMs on specialized cricket data.
- Where Did This Sentence Come From? Tracing Provenance in LLM Reasoning Distillation
Kaiyuan Liu, Shaotian Yan, Rui Miao, Bing Wang, Chen Shen · Dec 24, 2025
Reasoning distillation has attracted increasing attention.
- DIAL: Direct Iterative Adversarial Learning for Realistic Multi-Turn Dialogue Simulation
Ziyi Zhu, Olivier Tieleman, Caitlin A. Stamatis, Luka Smyth, Thomas D. Hull · Dec 23, 2025
Realistic user simulation is crucial for training and evaluating multi-turn dialogue systems, yet creating simulators that accurately replicate human behavior remains a significant challenge.
- On the Existence and Behavior of Secondary Attention Sinks
Jeffrey T. H. Wong, Cheng Zhang, Louis Mahon, Wayne Luk, Anton Isopoussu · Dec 22, 2025
Attention sinks are tokens, often the beginning-of-sequence (BOS) token, that receive disproportionately high attention despite limited semantic relevance.
- Stop saying LLM: Large Discourse Models (LDM) and Artificial Discursive Agent (ADA)?
Amar Lakel · Dec 22, 2025
This paper proposes an epistemological shift in the analysis of large generative models, replacing the category ''Large Language Models'' (LLM) with that of ''Large Discourse Models'' (LDM), and then with that of Artificial Discursive Agent
- Towards Efficient Agents: A Co-Design of Inference Architecture and System
Weizhe Lin, Hui-Ling Zhen, Shuai Yang, Xian Wang, Renxi Liu · Dec 20, 2025
Long Horizon
The rapid development of large language model (LLM)-based agents has unlocked new possibilities for autonomous multi-turn reasoning and tool-augmented decision-making.
- Knowledge Distillation with Structured Chain-of-Thought for Text-to-SQL
Khushboo Thaker, Yony Bresler · Dec 18, 2025
Deploying accurate Text-to-SQL systems at the enterprise level faces a difficult trilemma involving cost, security and performance.
- In-Context Algebra
Eric Todd, Jannik Brinkmann, Rohit Gandikota, David Bau · Dec 18, 2025
We investigate the mechanisms that arise when transformers are trained to solve arithmetic on sequences where tokens are variables whose meaning is determined only through their interactions in-context.
- Refusal Steering: Fine-grained Control over LLM Refusal Behaviour for Sensitive Topics
Iker García-Ferrero, David Montero, Roman Orus · Dec 18, 2025
Red Team
We replace fragile pattern-based refusal detection with an LLM-as-a-judge that assigns refusal confidence scores and we propose a ridge-regularized variant to compute steering vectors that better isolate the refusal--compliance direction.
- A Domain-Adapted Pipeline for Structured Information Extraction from Police Incident Announcements on Social Media
Mengfan Shen, Kangqi Song, Xindi Wang, Wei Jia, Tao Wang · Dec 18, 2025
Structured information extraction from police incident announcements is crucial for timely and accurate data processing, yet presents considerable challenges due to the variability and informal nature of textual sources such as social media
