1
Zoom In Disparities in Healthcare LLM Q&A
研究医疗大模型问答中的不公平现象，揭示不同人群间的表现差异。
arXiv:2510.17476v2 Announce Type: replace Abstract: Equitable access to reliable health information is vital when integrating AI into healthcare. Yet,…
2
LuxIT: A Luxembourgish Instruction Tuning Dataset from Monolingual Seed Data
卢森堡语大模型指令调优数据集LuxIT正式开源，独创单语种子数据高效构建方案，为低资源语言NLP突破奠定基础。
arXiv:2510.24434v3 Announce Type: replace Abstract: The effectiveness of instruction-tuned Large Language Models (LLMs) is often limited in low-resour…
3
Bridging Scientific Heritage: An Arabic--Russian Parallel Corpus and LLM Benchmark for Sustainable Knowledge Transfer
首个阿拉伯语-俄语平行语料库与LLM基准，打破科研语言壁垒，助力可持续发展知识交流。
arXiv:2606.30943v1 Announce Type: new Abstract: Russian and Arabic are among the major languages of scientific communication. Language barriers impede…
4
A Hybrid Framework for Song Lyric Annotation Based on Human-LLM Alignment
人类智慧与AI大模型协同，突破歌词标注的语义理解瓶颈
arXiv:2606.29273v1 Announce Type: new Abstract: Emotion recognition of song lyrics is a challenging task since lyrics may not necessarily align with t…
5
PatentScore: Multi-Dimensional Evaluation of LLM-Generated Patent Claims
来自EMNLP 2025，提出专利权利要求生成的多维评估基准，为LLM在专业文档生成领域提供新标尺。
Article URL: https://aclanthology.org/2025.emnlp-main.1564/ Comments URL: https://news.ycombinator.com/item?id=48683291 Points: 1 # Comments: 0
6
Show HN: Language1 – Benchmarking LLM comprehension of vague prompts via Taboo
用反向禁忌词游戏考察LLM对模糊提示的理解能力，创意与测试兼备。
Hi HN, I built Language1 ( https://language1.app ), a word game where you play "reverse Taboo" against an LLM. How it works: You are given a target wo…
7
Understanding LLM Reasoning for Abstractive Summarization
从推理到摘要：这篇论文系统研究了通用推理策略如何适应抽象文本摘要，揭示LLM推理能力的新边界。
arXiv:2512.03503v3 Announce Type: replace Abstract: Reasoning has substantially improved Large Language Models (LLMs) on analytical tasks such as math…
8
Do LLMs Reliably Identify Correct Information Units in Aphasic Discourse?
大模型能否精准识别失语症话语中的信息单元？这项研究评估指令调优LLM在临床语篇评估中的可靠性。
arXiv:2606.15696v1 Announce Type: new Abstract: Correct Information Units (CIUs) are central to discourse assessment in aphasia because they quantify …
9
M\"OVE: A Holistic LLM Benchmark for the German Public Sector
首个专为德国公共部门设计的LLM综合基准，评估行政、法律等场景的模型表现。
arXiv:2606.13111v1 Announce Type: new Abstract: We present M\"OVE (Modelle f\"ur die \"Offentliche Verwaltung Evaluieren), a holistic benchmark for ev…
10
How Far Can Prompting Go for Minimal-Edit Ukrainian Grammatical Error Correction?
探索提示工程在低资源语言乌克兰语上的语法纠错极限，揭示大模型与提示策略的边界。
arXiv:2606.09334v1 Announce Type: new Abstract: Fine-tuned Large Language Models (LLMs) dominate in Ukrainian grammatical error correction (GEC), whil…
11
Massively Multilingual Joint Segmentation and Glossing
大规模多语言联合分词与标注方法，ACL 2026长文带来NLP新突破。
arXiv:2601.10925v3 Announce Type: replace Abstract: Automated interlinear gloss prediction with neural networks is a promising approach to accelerate …
12
Inside the LLM Word Factory
揭秘大模型内部单词生成的完整流水线，从原理到图表示，一篇学术深研论文。
arXiv:2606.08562v1 Announce Type: new Abstract: Transformer language models process input provided as subword fragments, but natural language semantic…
13
SciTrace: Trajectory-Aware Safety Reasoning for Scientific Discovery Agents
MIT新研究提出轨迹感知安全推理方法，让科学发现AI更安全可靠
arXiv:2606.08234v1 Announce Type: new Abstract: LLM-based scientific agents have shown strong capacity for autonomous research, yet their safety layer…
14
TQA-Bench: Evaluating LLMs for Multi-Table Question Answering
新基准TQA-Bench专测大模型多表问答能力，揭示多表关联推理的挑战与局限。
arXiv:2411.19504v2 Announce Type: replace-cross Abstract: The advance of large language models (LLMs) has unlocked great opportunities in complex mult…
15
Summarization is Not Dead Yet
这篇2026年的论文证明文本摘要任务在大模型时代依然充满生命力，挑战了“摘要已死”的观点。
arXiv:2606.08000v1 Announce Type: new Abstract: The progress of large language models (LLMs) has fueled claims that model-generated summaries rival or…
16
Beyond English benchmarks: clinical llm evaluation in Brazilian Portuguese
突破英语局限，首次系统评估大型语言模型在巴西葡语临床场景的表现
arXiv:2606.07853v1 Announce Type: new Abstract: Large Language Models are transforming the support for clinical decision and their application in real…
17
DECSELFMASK: Leveraging Unlabeled Text via Self-Relevance-Guided Masking for Decoder-Only Classification
自监督掩码学习突破标注瓶颈，医疗等场景下用无标签文本提升分类性能。
arXiv:2606.09466v1 Announce Type: new Abstract: Classification tasks require annotated data, which can often be expensive, time-consuming, or even unf…
18
Towards One-to-Many Temporal Grounding
ICML'26接收，提出一对多时序定位新框架，突破传统单片段局限，实现文本到视频多片段精准匹配。
arXiv:2606.06294v1 Announce Type: cross Abstract: Temporal Grounding (TG) aims to localize video segments corresponding to a textual query. Prior rese…
19
Consistency Training Along the Transformer Stack
Transformer一致性训练机制，通过堆叠层间约束提升模型表现与稳定性。
arXiv:2606.05817v1 Announce Type: cross Abstract: Consistency training encourages models to behave similarly across different contexts, and has shown …
20
Improving Answer Extraction in Context-based Question Answering Systems Using LLMs
利用大语言模型提升基于上下文的问答系统答案提取准确率，提供了实验验证与新思路。
arXiv:2606.06197v1 Announce Type: cross Abstract: Question answering (QA) systems have achieved notable progress with the advent of large language mod…