Latest Text Summarization Research Papers

The newest Text Summarization papers from across the field — arXiv, NeurIPS, CVPR, Nature, and more — refreshed daily and ranked by relevance. Distill AI tracks Text Summarization so you don’t have to: get the standout work delivered to your inbox every morning, with 2-sentence summaries and the option to chat with any paper.

Recent papers

• Medical gases and hypertensive disorders of pregnancy: therapeutic mechanisms and research advances.
  Zhiguang Xu, Tian Geng, Di Zhou, Fuju Wu · PubMed Central · Jan 1, 2027

  Hypertensive disorders during pregnancy pose a serious threat to the health of both mothers and infants, yet the range of available clinical treatments is limited. This review summarizes the mechanisms and recent advances in the use of medi…

• Text summarization via global structure awareness
  Jiaquan Zhang, Chaoning Zhang, Shuxu Chen, Yibei Liu et al. · CoRR 2026 · Dec 31, 2026

  Text summarization is a fundamental task in natural language processing (NLP), and the information explosion has made long-document processing increasingly demanding, making summarization essential. Existing research mainly focuses on model…

• Homebrewed SLMs: Autoregressive and Masked Diffusion Language Models Built at Home for Portuguese
  Pedro Carvalho Brom · arXiv · Oct 29, 2026

  Building a language model of one's own no longer requires a data centre. This tutorial trains one from scratch, tokenizer included, on one consumer GPU, and shows how to tell whether it is good for the tasks of a specialist domain. It propo…

• CulturalRiddles: A Multicultural Benchmark of Riddles
  My Chiffon Nguyen, Tianyi Hu, Vinod Anbalagan, Henry Gagnier et al. · arXiv · Oct 21, 2026

  As LLMs expand their language coverage, evaluating how well they understand and represent diverse cultures becomes increasingly important. However, many benchmarks remain English-centric, with limited cultural coverage and a focus on factua…

• NarraSpace: Multimodal Scene-Grounded Evidence for Picture-Description Dementia Classification
  Qingming Li, Ruiyan Sun, Satoshi Nakamura · arXiv · Oct 20, 2026

  Picture-description dementia classification uses a shared visual scene, but a transcript-level prediction alone does not identify the scene evidence underlying its inputs. NarraSpace links words and speech times to named picture elements an…

• Beyond a Single Sentiment Score: Topical and Affective Dimensions of Emoji Meaning on Twitter
  Rohan James, Ioannis Christofilogiannis, Yuuv Jauhari, Shreya Shah et al. · arXiv · Oct 20, 2026

  Emoji are widely treated as compact affective tokens whose meaning is summarised by a single sentiment score. We argue that this picture is incomplete. From a corpus of 16{,}575 English tweets and a per-emoji metric we call \emph{stability …

• BAIT: Can LLMs Find What Biases a Reader? A Benchmark for Cognitive Bias Triggers in News
  Yousra Fettach, Tijl De Bie · arXiv · Oct 20, 2026

  Persuasive writing exploits cognitive biases, recruiting a reader's mental shortcuts to shape belief, often without the reader noticing. We call the linguistic features exploiting such mental shortcuts cognitive bias triggers. As large lang…

• When the harness decides success: state that cannot be re-observed
  Raimondas Lencevicius · arXiv · Oct 19, 2026

  Agent harnesses decide what a language model sees across turns: they drop old turns, summarize them, or replay the model's own earlier reasoning. We ask when these choices change whether an agent succeeds, not only what it costs, and report…

• Abstracts or full text? Evaluating input scope and computational efficiency in biomedical lay summarization
  Egecan Çelik Evgin, İlknur Karadeniz, Olcay Taner Yıldız · arXiv · Oct 15, 2026

  Biomedical research articles are mainly written for experts and often contain terms that are difficult for the general public to understand. Automated lay summarization has become a solution to make biomedical knowledge easier for patients …

• ChronoCulture: Evaluating Cultural Awareness Across Time in Large Language Models
  Rusali Saha, Nitya Khurana, Ruihong Huang, Kuan-Hao Huang · arXiv · Oct 14, 2026

  Cultural attitudes and social norms evolve over time, yet most cultural benchmarks for large language models (LLMs) treat culture as a static attribute of a country or region. We introduce ChronoCulture, a benchmark of 10,360 temporal pairs…

• Share the Symbol, Not the Vector: Training-Free Fact Communication Across Language Models
  Xin Li, Mengbing Liu, Hao Jiang, Xin Gao et al. · arXiv · Oct 14, 2026

  Multi-agent systems allow language models to solve tasks collaboratively by sharing complementary information. These systems typically communicate through text, while recent approaches also explore exchanging internal model states. However,…

• Fish Audio Drama 3 Technical Report
  Dawei Han, Shidong Li, Shijia Liao, Jiahua Liu et al. · arXiv · Oct 13, 2026

  We introduce Fish Audio Drama 3, an open-source speech generation model that turns text into directed performances, built on a 35B-parameter mixture-of-experts backbone that activates 3B parameters per token. It clones voices from multiple …

• Same Outcome, Different Evidence: Intent Recovery in LLM Safety Evaluation
  Haitong Jiang, Chunlin Liu, Sihan Tang, Chan Wu et al. · arXiv · Oct 8, 2026

  Safety evaluations of large language models commonly summarize harmful-output behavior with attack success rate (ASR). Yet the same non-harmful outcome can arise for very different reasons. A model may recover a harmful task and refuse it, …

• Decoupling Exploration from Optimization in RLVR
  Saif Punjwani, Micah Goldblum · arXiv · Oct 7, 2026

  Modern language models undergo reinforcement learning with verifiable rewards (RLVR) on top of already-trained checkpoints. A key promise of RLVR is the discovery of new reasoning strategies. In principle, a model can sample novel ideas abs…

• A Comparative Study of Evaluation Metrics for Long-Document Financial Narrative Summarization with Transformers
  Nadhem Zmandar, Mo El-Haj, Paul Rayson · arXiv · Oct 7, 2026

  There are more than 2,000 listed companies on the UK's London Stock Exchange, divided into 11 sectors who are required to communicate their financial results at least twice in a single financial year. UK annual reports are very lengthy docu…

• IdeaLens: Detecting AI Ideas in Long-form Writing
  Rishanth Rajendhran, Minjoon Choi, Jenna Russell, Ramya Namuduri et al. · arXiv · Oct 5, 2026

  While modern AI detectors identify who wrote the words, emerging policies on AI use increasingly hinge on a different question: who came up with the ideas? We introduce IdeaLens, a detector that identifies whether a document's ideas came fr…

• Learning to Learn a Language
  Lennart Carstens-Behrens, Holger Fröhlich · arXiv · Oct 5, 2026

  We present the Prior-Fitted Language Model (PFLM), a 300M-parameter byte-level transformer pretrained only on samples from a synthetic non-linguistic prior. Given a prefix of real text, it learns to predict the language in context with froz…

• Evaluating LLM-as-a-Judge Beyond Score Alignment: A Psychometric Analysis of Residual Judging Difficulty
  Longwei Cong, Sonja Hahn, Sebastian Gombert, Leon Camus et al. · arXiv · Oct 2, 2026

  Large language models (LLMs) are widely used as automatic judges, with validity typically assessed via alignment with human scores. However, aggregate agreement fails to reveal whether humans and LLMs find the same evaluation cases difficul…

• Persistent Context Graphs for Efficient Memory Compaction in LLM Agents
  Jingbo Yang, Kwei-Herng Lai, Xiaowen Wang, Zhaoxuan Tan et al. · arXiv · Sep 30, 2026

  As LLM capabilities advance, agents are tackling increasingly complex tasks over longer horizons. Their growing interaction histories make memory compaction essential for staying within context windows and reducing prefill cost. Existing me…

• QuanReview: Offline, Auditable Reconciliation of Human and LLM Span Annotations
  Matteo Musacchio, Juan Cruz Giner Pulero, Isabel Castañeda, Naomi Couriel et al. · arXiv · Sep 28, 2026

  Structured span annotations, such as quantities with their units, uncertainty modifiers, and event classes, are expensive to create and hard to keep trustworthy once language models enter the loop. We present QuanReview, an open-source syst…

• Towards Mitigating Fabricated Consensus: The Active Provenance Gate for Multi-Agent Debate Synthesis
  Jakub Masłowski, Jarosław A. Chudziak · arXiv · Sep 25, 2026

  Large language model-based multi-agent debate (MAD) systems are being increasingly used as complex decision pipelines in distributed processes. However, their final synthesis phase still remains inadequately controlled. Even with detailed d…

• Highlight-Then-Summarize: Learning to Compress Evidence for Long-Context Understanding
  Zhaoyuan Xia, Qinghongbing Xie, Yung Xiang Hue, Jianguang Jiang et al. · arXiv · Sep 25, 2026

  Long-context understanding requires large language models (LLMs) to reason over lengthy documents, conversations, and code, yet task-relevant evidence is often sparse and scattered amid substantial irrelevant and redundant content. We propo…

• PIA: A Personal Intelligence Agent Turning Health Conversations into Records and Records into Understanding
  Jeonghun Yoon, Dongchan Kim, Hongyeon Yu, Young-Bum Kim et al. · arXiv · Sep 25, 2026

  General-purpose agent memory summarizes conversations: it extracts salient snippets, embeds them, and retrieves the top-k into the prompt. A health agent cannot run on summaries: a dose becomes a sentence, "since last week" is resolved at t…

• Coupled Usage-Sense Processes: Temporal and Attributable Lexical Semantic Change
  Haruka Ezoe, Ryohei Hisano · arXiv · Sep 25, 2026

  Lexical semantic change is usually summarized by a scalar distance between independently sampled period distributions. This measures how much a word changed, but does not reveal when it changed, which mechanisms and component movements carr…

• Effects of Transcript Compression on LLM-based Medical Misinformation Detection in Japanese YouTube Videos
  Yuya Wake, Sho Tsugawa, Toshiyuki Amagasa · arXiv · Sep 25, 2026

  Large language models (LLMs) are increasingly used to assess long-form medical videos, but their effectiveness may depend on whether transcripts are provided in full or compressed through summarization, retrieval, or claim screening. This s…

• Controlled Attribute-Specific Summarization of Interrogative Dialogues
  A Aditya Bhardwaj, Arjit Singh Arora, Md Shad Akhtar · arXiv · Sep 23, 2026

  Effective summarization of interrogative dialogues is a critical task in forensic and investigative settings, requiring high factual accuracy, coherence, and attribute-specific relevance. In this work, we introduce CASPER, a novel Chain-of-…

• Can One Adapted Model Do It All? Fine-Tuning Strategy Selection for Customer Support LLMs
  Md Tahmid Rahman Laskar, Xue-Yong Fu, Shashi Bhushan TN · arXiv · Sep 23, 2026

  Production customer-support systems often require LLMs to support multiple skills, such as intent classification, question answering, summarization, or tool-use decisions. A central deployment question is whether these skills should be hand…

• MSI-Bench: Evaluating Multi-Speaker Voice Interaction for Collaborative AI Agents
  Chenxu Xiong, Dongming Shen, Yuzhi Tang, Wentao Ma et al. · arXiv · Sep 21, 2026

  Voice provides a natural and immediate interface for AI agents. Many settings in which voice agents could be useful, including meetings, households, and collaborative work, are inherently multi-speaker. Supporting these settings introduces …

• When Evidence Conflicts: Reliability-aware Meta-review Generation
  Xinzhe Wang, Fei Tao, Jiang Xie, Hong Yu et al. · arXiv · Sep 21, 2026

  Generating coherent meta-reviews from multiple peer reviews is challenging when reviewer evidence conflicts and varies in reliability. Existing approaches typically formulate meta-review generation as a multi-document summarization task and…

• Summarization Bias: The Directional Collapse of Objective Projection into Told-Mode Labels in Large Language Models --- A Conceptual Framework and Registered Test Protocol
  Levent Bulut · arXiv · Sep 17, 2026

  This paper introduces and operationalizes summarization bias: a proposed systematic tendency of large language models (LLMs) to represent narrative meaning as an abstract summary label rather than as the reconstructable inferential structur…