- Discourse-Aware Dual-Track Streaming Response for Low-Latency Spoken Dialogue Systems
Siyuan Liu, Jiahui Xu, Feng Jiang, Kuang Wang, Zefeng Zhao · Feb 26, 2026
Automatic Metrics General
Achieving human-like responsiveness is a critical yet challenging goal for cascaded spoken dialogue systems.
- Stop-Think-AutoRegress: Language Modeling with Latent Diffusion Planning
Justin Lovelace, Christian Belardi, Sofian Zalouk, Adhitya Polavaram, Srivatsa Kundurthy · Feb 24, 2026
Llm As JudgeAutomatic Metrics General
Evaluations show STAR-LDM significantly outperforms similar-sized models on language understanding benchmarks and achieves $>70\%$ win rates in LLM-as-judge comparisons for narrative coherence and commonsense reasoning.
- KGHaluBench: A Knowledge Graph-Based Hallucination Benchmark for Evaluating the Breadth and Depth of LLM Knowledge
Alex Robertson, Huizhi Liang, Mahbub Gani, Rohit Kumar, Srijith Rajamohan · Feb 23, 2026
Automatic Metrics General
Existing benchmarks are limited by static and narrow questions, leading to limited coverage and misleading evaluations.
- Facet-Level Persona Control by Trait-Activated Routing with Contrastive SAE for Role-Playing LLMs
Wenqiu Tang, Zhen Wan, Takahiro Komamizu, Ichiro Ide · Feb 22, 2026
Automatic Metrics Coding
Personality control in Role-Playing Agents (RPAs) is commonly achieved via training-free methods that inject persona descriptions and memory through prompts or retrieval-augmented generation, or via supervised fine-tuning (SFT) on persona-s
- Decomposing Retrieval Failures in RAG for Long-Document Financial Question Answering
Amine Kobeissi, Philippe Langlais · Feb 20, 2026
Automatic Metrics Coding
Retrieval-augmented generation is increasingly used for financial question answering over long regulatory filings, yet reliability depends on retrieving the exact context needed to justify answers in high stakes settings.
- Improving Neural Topic Modeling with Semantically-Grounded Soft Label Distributions
Raymond Li, Amirhossein Abaskohi, Chuyuan Li, Gabriel Murray, Giuseppe Carenini · Feb 20, 2026
Automatic Metrics General
Traditional neural topic models are typically optimized by reconstructing the document's Bag-of-Words (BoW) representations, overlooking contextual information and struggling with data sparsity.
- AIDG: Evaluating Asymmetry Between Information Extraction and Containment in Multi-Turn Dialogue
Adib Sakhawat, Fardeen Sadab, Rakin Shahriar · Feb 19, 2026
Automatic Metrics General
Evaluating the strategic reasoning capabilities of Large Language Models (LLMs) requires moving beyond static benchmarks to dynamic, multi-turn interactions.
- Reinforced Fast Weights with Next-Sequence Prediction
Hee Seung Hwang, Xindi Wu, Sanghyuk Chun, Olga Russakovsky · Feb 18, 2026
Automatic Metrics General
Fast weight architectures offer a promising alternative to attention-based transformers for long-context modeling by maintaining constant memory overhead regardless of context length.
- Protecting Language Models Against Unauthorized Distillation through Trace Rewriting
Xinhang Ma, William Yeoh, Ning Zhang, Yevgeniy Vorobeychik · Feb 16, 2026
Automatic Metrics General
Knowledge distillation is a widely adopted technique for transferring capabilities from LLMs to smaller, more efficient student models.
- Document Reconstruction Unlocks Scalable Long-Context RLVR
Yao Xiao, Lei Wang, Yue Deng, Guanzheng Chen, Ziqi Jin · Feb 9, 2026
Automatic Metrics Coding
However, it often relies on gold-standard answers or explicit evaluation rubrics provided by powerful teacher models or human experts, which are costly and time-consuming.
- KD-OCT: Efficient Knowledge Distillation for Clinical-Grade Retinal OCT Classification
Erfan Nourbakhsh, Nasrin Sanjari, Ali Nourbakhsh · Dec 9, 2025
Automatic Metrics MedicineCoding
Age-related macular degeneration (AMD) and choroidal neovascularization (CNV)-related conditions are leading causes of vision loss worldwide, with optical coherence tomography (OCT) serving as a cornerstone for early detection and managemen
- Beyond Fact Retrieval: Episodic Memory for RAG with Generative Semantic Workspaces
Shreyas Rajesh, Pavan Holur, Chenda Duan, David Chong, Vwani Roychowdhury · Nov 10, 2025
Automatic Metrics Coding
On the Episodic Memory Benchmark (EpBench) \cite{huet_episodic_2025} comprising corpora ranging from 100k to 1M tokens in length, GSW outperforms existing RAG based baselines by up to \textbf{20\%}.
- Beyond a Million Tokens: Benchmarking and Enhancing Long-Term Memory in LLMs
Mohammad Tavakoli, Alireza Salemi, Carrie Ye, Mohamed Abdalla, Hamed Zamani · Oct 31, 2025
Automatic Metrics General
Evaluating the abilities of large language models (LLMs) for tasks that require long-term memory and thus long-context reasoning, for example in conversational settings, is hampered by the existing benchmarks, which often lack narrative coh
- Structure-Augmented Reasoning Generation
Jash Rajesh Parekh, Pengcheng Jiang, Jiawei Han · Jun 10, 2025
Automatic Metrics General
Extensive experiments on open-domain QA benchmarks and specialized reasoning datasets in finance and medicine demonstrate that SARG significantly outperforms state-of-the-art flat-context RAG baselines in both factual accuracy and reasoning
- Beyond Single-Turn: A Survey on Multi-Turn Interactions with Large Language Models
Yubo Li, Xiaobin Shen, Xinyu Yao, Xueying Ding, Yidi Miao · Apr 7, 2025
Automatic Metrics Math
We organize existing benchmarks and datasets into coherent categories reflecting the evolving landscape of multi-turn dialogue evaluation, and review a broad spectrum of enhancement methodologies, including model-centric strategies (in-cont
