Text Generation

Follow this topic Ask about this topic

Text generation studies how models produce language for tasks such as dialogue, summarization, storytelling, translation, and structured reports. Autoregressive transformers generate token by token, while masked-diffusion and flow-based models explore parallel or few-step generation; decoding and activation steering offer ways to adjust outputs without retraining. For longer or constrained tasks, systems combine planning, retrieval, structured representations, editing, and feedback-based training such as reinforcement learning. A central challenge is balancing speed and instruction-following with factuality, diversity, cultural fit, and quality that human readers and domain experts value.

Latest papers

423 papers51 papers in the last four weeks, up 24% on the four weeks before. 0.3% of all new papers.

Feb 22, 2026

Next Reply Prediction X Dataset: Linguistic Discrepancies in Naively Generated Content

The increasing use of Large Language Models (LLMs) as proxies for human participants in social science research presents a promising, yet methodologically risky, paradigm shift. While LLMs offer scalability and cost-efficiency, their "naive" application, where they are prompted to generate content without explicit behavioral constraints, introduces significant linguistic discrepancies that challenge the validity of research findings. This paper addresses these limitations by introducing a novel, history-conditioned reply prediction task on authentic X (formerly Twitter) data, to create a dataset designed to evaluate the linguistic output of LLMs against human-generated content. We analyze these discrepancies using stylistic and content-based metrics, providing a quantitative framework for researchers to assess the quality and authenticity of synthetic data. Our findings highlight the need for more sophisticated prompting techniques and specialized datasets to ensure that LLM-generated content accurately reflects the complex linguistic patterns of human communication, thereby improving the validity of computational social science studies.

Simon Münker, Nils Schwager, Kai Kugler +2

Trier University, Computational Linguistics · University of Oxford, Sociology

Language Model Generation Evaluation Text Generation Large Language Model-Based Social Simulation Synthetic Data Generation for Language Models

Feb 19, 2026

PEACE 2.0: Grounded Explanations and Counter-Speech for Combating Hate Expressions

The increasing volume of hate speech on online platforms poses significant societal challenges. While the Natural Language Processing community has developed effective methods to automatically detect the presence of hate speech, responses to it, called counter-speech, are still an open challenge. We present PEACE 2.0, a novel tool that, besides analysing and explaining why a message is considered hateful or not, also generates a response to it. More specifically, PEACE 2.0 has three main new functionalities: leveraging a Retrieval-Augmented Generation (RAG) pipeline i) to ground HS explanations into evidence and facts, ii) to automatically generate evidence-grounded counter-speech, and iii) exploring the characteristics of counter-speech replies. By integrating these capabilities, PEACE 2.0 enables in-depth analysis and response generation for both explicit and implicit hateful messages.

Greta Damo, Stéphane Petiot, Elena Cabrio +1

Université Côte d’Azur, CNRS, Inria, I3S, France · Université Côte d’Azur, Institut 3IA Côte d’Azur, Techpool, France

Text Generation Hate Speech Detection

Feb 19, 2026

Exploring LLMs for User Story Extraction from Mockups

User stories are one of the most widely used artifacts in the software industry to define functional requirements. In parallel, the use of high-fidelity mockups facilitates end-user participation in defining their needs. In this work, we explore how combining these techniques with large language models (LLMs) enables agile and automated generation of user stories from mockups. To this end, we present a case study that analyzes the ability of LLMs to extract user stories from high-fidelity mockups, both with and without the inclusion of a glossary of the Language Extended Lexicon (LEL) in the prompts. Our results demonstrate that incorporating the LEL significantly enhances the accuracy and suitability of the generated user stories. This approach represents a step forward in the integration of AI into requirements engineering, with the potential to improve communication between users and developers.

Diego Firmenich, Leandro Antonelli, Bruno Pazos +2

Departamento de Informática, Facultad de Ingeniería, Universidad Nacional de la Patagonia, Argentina · LIFIA, Facultad de Informática, Universidad Nacional de La Plata, Argentina · CAETI, Facultad de Tecnología Informática - Universidad Abierta Interamericana +3

Requirements Engineering Text Generation LLM Prompting Knowledge Augmentation for Language Models

Feb 18, 2026

Meenz bleibt Meenz, but Large Language Models Do Not Speak Its Dialect

Meenzerisch, the dialect spoken in the German city of Mainz, is also the traditional language of the Mainz carnival, a yearly celebration well known throughout Germany. However, Meenzerisch is on the verge of dying out-a fate it shares with many other German dialects. Natural language processing (NLP) has the potential to help with the preservation and revival efforts of languages and dialects. However, so far no NLP research has looked at Meenzerisch. This work presents the first research in the field of NLP that is explicitly focused on the dialect of Mainz. We introduce a digital dictionary-an NLP-ready dataset derived from an existing resource (Schramm, 1966)-to support researchers in modeling and benchmarking the language. It contains 2,351 words in the dialect paired with their meanings described in Standard German. We then use this dataset to answer the following research questions: (1) Can state-of-the-art large language models (LLMs) generate definitions for dialect words? (2) Can LLMs generate words in Meenzerisch, given their definitions? Our experiments show that LLMs can do neither: the best model for definitions reaches only 6.27% accuracy and the best word generation model's accuracy is 1.51%. We then conduct two additional experiments in order to see if accuracy is improved by few-shot learning and by extracting rules from the training set, which are then passed to the LLM. While those approaches are able to improve the results, accuracy remains below 10%. This highlights that additional resources and an intensification of research efforts focused on German dialects are desperately needed.

Minh Duc Bui, Manuel Mager, Peter Herbert Kann +1

Johannes Gutenberg University Mainz, Germany · Marburg University, Germany · University of Colorado Boulder, USA

Low-Resource Language Processing Text Generation Language Model Generation Evaluation

Feb 18, 2026

Creating a digital poet

Can a machine write good poetry? Any positive answer raises fundamental questions about the nature and value of art. We report a seven-month poetry workshop in which a large language model was shaped into a digital poet through iterative in-context expert feedback, without retraining. Across sessions, the model developed a distinctive style and a coherent corpus, supported by quantitative and qualitative analyses, and it produced a pen name and author image. In a blinded authorship test with 50 humanities students and graduates (three AI poems and three poems by well-known poets each), judgments were at chance: human poems were labeled human 54% of the time and AI poems 52%, with 95% confidence intervals including 50%. After the workshop, a commercial publisher released a poetry collection authored by the model. These results show that workshop-style prompting can support long-horizon creative shaping and renew debates on creativity and authorship.

Vered Tohar, Tsahi Hayat, Amir Leshem

Department of Jewish Literature, Bar-Ilan University, Ramat-Gan, Israel. · Department of Communication, Reichman University, Hertzeliya, Israel. · Faculty of Engineering, Bar-Ilan University, Ramat-Gan, Israel.

Computational Creativity Text Generation Human-AI Co-Creation Language Model Generation Evaluation

Feb 18, 2026

LLMs Exhibit Significantly Lower Uncertainty in Creative Writing Than Professional Writers

We argue that uncertainty is a key and understudied limitation of LLMs' performance in creative writing, which is often characterized as trite and cliché-ridden. Literary theory identifies uncertainty as a necessary condition for creative expression, while current alignment strategies steer models away from uncertain outputs to ensure factuality and reduce hallucination. We formalize this tension by quantifying the ``uncertainty gap'' between human-authored stories and model-generated continuations. Through a controlled information-theoretic analysis of 28 LLMs on high-quality storytelling datasets, we demonstrate that human writing consistently exhibits significantly higher uncertainty than model outputs. We find that instruction-tuned and reasoning models exacerbate this trend compared to their base counterparts; furthermore, the gap is more pronounced in creative writing than in functional domains, and shows a consistent correlation with writing quality. Achieving human-level creativity requires new uncertainty-aware alignment paradigms that can distinguish between destructive hallucinations and the constructive ambiguity required for literary richness.

Peiqi Sui

Department of English, McGill University

Text Generation Computational Creativity Language Model Generation Evaluation LLM Uncertainty Estimation

Feb 17, 2026

BTReport: A Framework for Brain Tumor Radiology Report Generation with Clinically Relevant Features

Recent advances in radiology report generation (RRG) have been driven by large paired image-text datasets; however, progress in neuro-oncology has been limited due to a lack of open paired image-report datasets. Here, we introduce BTReport, an open-source framework for brain tumor RRG that constructs natural language radiology reports using deterministically extracted imaging features. Unlike existing approaches that rely on large general-purpose or fine-tuned vision-language models for both image interpretation and report composition, BTReport performs deterministic feature extraction for image analysis and uses large language models only for syntactic structuring and narrative formatting. By separating RRG into a deterministic feature extraction step and a report generation step, the generated reports are completely interpretable and less prone to hallucinations. We show that the features used for report generation are predictive of key clinical outcomes, including survival and IDH mutation status, and reports generated by BTReport are more closely aligned with reference clinical reports than existing baselines for RRG. Finally, we introduce BTReport-BraTS, a companion dataset that augments BraTS imaging with synthetically generated radiology reports produced with BTReport. Code for this project can be found at https://github.com/KurtLabUW/BTReport.

Juampablo E. Heras Rivera, Dickson T. Chen, Tianyi Ren +4

University of Washington · University of Washington School of Medicine · Microsoft Health AI +1

Radiology Report Generation Text Generation Explainable Medical Image Analysis

Feb 16, 2026

ScrapeGraphAI-100k: Dataset for Schema-Constrained LLM Generation

Producing output that conforms to a specified JSON schema underlies tool use, structured extraction, and knowledge base construction in modern large language models. Despite this centrality, public datasets for the task remain small, synthetic, or text-only, and rarely pair real page content with the prompts and schemas used in practice. We introduce ScrapeGraphAI-100k, 93,695 schema-constrained extraction events collected via opt-in ScrapeGraphAI telemetry in Q2--Q3 2025, deduplicated and balanced by schema from 9M raw events. The corpus spans 18 000+ unique schemas across 15 named languages plus a long-tail Other category, with English and Traditional Chinese covering 88% of detected content, each instance pairs Markdown-converted page content with a prompt, schema, LLM response, and per-example jsonschema-rs structural conformance labels (semantic correctness is out of scope, and raw HTML is deferred beyond v1.0). We characterize structural diversity across the corpus and identify sharp failure thresholds as schema complexity grows. As a case study, a 1.7B student fine-tuned on this data closely tracks the output distribution of its GPT-5-nano teacher, though it still trails a 30B-A3B reference (3.3B active parameters) on schema compliance. We offer this distillation result as preliminary evidence that grounding schema-constrained generation in real practitioner workloads at scale enables training and benchmarking that prior synthetic or text-only corpora could not support.

William Brach, Francesco Zuppichini, Marco Vinciguerra +1

ScrapeGraphAI, San Francisco, United States

Schema-Constrained Generation LLM Information Extraction Text Generation Document Information Extraction Language Model Generation Evaluation

Feb 16, 2026

RT-SFT: Text Style Transfer from Non-Parallel Corpora by Roundtrip Translation

Text style transfer (TST) is naturally a supervised task - rewrite a sentence in a target style while preserving its meaning - yet the parallel corpora that supervision requires exist for only a handful of style domains. A common workaround is to normalize an input into a style-agnostic intermediate and then stylize it into the target style, but the normalizer is typically a lightweight, task-specific paraphraser applied only at test time, feeding a correspondingly small stylizer. We observe that a style-stripping normalizer already exists at scale: neural MT systems trained on hundreds of millions of general-domain sentence pairs preserve content while regressing toward generic phrasing, so roundtrip translation through a pivot language strips stylistic signal without any task-specific training. This turns normalization from an inference-time patch into a data-generation tool. Roundtrip-translating a monolingual in-style corpus yields a pseudo-parallel corpus on which we LoRA-finetune an instruction-tuned LLM as the stylizer (RT-SFT); applying the same normalizer to test queries keeps that stylizer in-distribution. We show that across four style domains, RT-SFT outperforms state-of-the-art methods, such as few-shot in-context learning, by considerable margins. We also report on effective retrieval augmentation methods for expert style domains with strict terminology and naming conventions.

Ruoxi Liu, Philipp Koehn

Text Style Transfer Text Generation LLM Fine-Tuning

Feb 16, 2026

Multi-Agent Comedy Club: Investigating Community Discussion Effects on LLM Humor Generation

Prior work has explored multi-turn interaction and feedback for LLM writing, but evaluations still largely center on prompts and localized feedback, leaving persistent public reception in online communities underexamined. We test whether broadcast community discussion improves stand-up comedy writing in a controlled multi-agent sandbox: in the discussion condition, critic and audience threads are recorded, filtered, stored as social memory, and later retrieved to condition subsequent generations, whereas the baseline omits discussion. Across 50 rounds (250 paired monologues) judged by five expert annotators using A/B preference and a 15-item rubric, discussion wins 75.6% of instances and improves Craft/Clarity (Δ = 0.440) and Social Response (Δ = 0.422), with occasional increases in aggressive humor.

Shiwei Hong, Lingyao Li, Ethan Z. Rong +2

George Mason University · University of South Florida · University of Toronto

Humor Explanation Generation Text Generation Language Model Generation Evaluation Multi-Agent Communication

Feb 13, 2026

CLASE: A Hybrid Method for Chinese Legalese Stylistic Evaluation

Legal text generated by large language models (LLMs) can usually achieve reasonable factual accuracy, but it frequently fails to adhere to the specialised stylistic norms and linguistic conventions of legal writing. In order to improve stylistic quality, a crucial first step is to establish a reliable evaluation method. However, having legal experts manually develop such a metric is impractical, as the implicit stylistic requirements in legal writing practice are difficult to formalise into explicit rubrics. Meanwhile, existing automatic evaluation methods also fall short: reference-based metrics conflate semantic accuracy with stylistic fidelity, and LLM-as-a-judge evaluations suffer from opacity and inconsistency. To address these challenges, we introduce CLASE (Chinese LegAlese Stylistic Evaluation), a hybrid evaluation method that focuses on the stylistic performance of legal text. The method incorporates a hybrid scoring mechanism that combines 1) linguistic feature-based scores and 2) experience-guided LLM-as-a-judge scores. Both the feature coefficients and the LLM scoring experiences are learned from contrastive pairs of authentic legal documents and their LLM-restored counterparts. This hybrid design captures both surface-level features and implicit stylistic norms in a transparent, reference-free manner. Experiments on 200 Chinese legal documents show that CLASE achieves substantially higher alignment with human judgments than traditional metrics and pure LLM-as-a-judge methods. Beyond improved alignment, CLASE provides interpretable score breakdowns and suggestions for improvements, offering a scalable and practical solution for professional stylistic evaluation in legal text generation (Code and data for CLASE is available at: https://github.com/rexera/CLASE).

Yiran Rex Ma, Yuxiao Ye, Huiyuan Xie

School of Foreign Languages, Peking University · Department of Computer Science and Technology, Tsinghua University

Automated Evaluation Legal NLP Stylometry Text Generation LLM-as-a-Judge

Feb 9, 2026

GitSearch: Enhancing Community Notes Generation with Gap-Informed Targeted Search

Community Notes enable scalable, community-based fact-checking, but automated generation faces a coverage--quality trade-off. Note-dependent methods (e.g., summarization-based Supernotes) cannot operate without prior crowd input, while web-search LLMs achieve broad coverage but often retrieve evidence misaligned with what raters need. We introduce GitSearch (Gap-Informed Targeted Search), which treats missing, ambiguous, or disputed information as first-class retrieval targets. It infers information gaps from a post and optional incomplete notes, searches specifically to resolve them, and synthesizes an evidence-grounded Community Note. To evaluate this, we introduce PolBench, a new dataset of 78,698 U.S. political tweets with Community Notes. Keeping single-call search inference budget fixed, GitSearch improves human-rated helpfulness by 0.43 over unconditioned web search and wins 59% of pairwise comparisons. It generates notes for 99% of test cases, including the 46% where summarization methods fail. Human evaluators prefer GitSearch to human-written helpful notes in 69% of comparisons, primarily due to better context coverage. These findings show that how search is organized matters more than information access alone.

Sahajpreet Singh, Kokil Jaidka, Min-Yen Kan +1

National University of Singapore

Automated Fact-Checking Evidence Retrieval Text Generation

Feb 4, 2026

CoT is Not the Chain of Truth: An Empirical Internal Analysis of Reasoning LLMs for Fake News Generation

From generating headlines to fabricating news, the Large Language Models (LLMs) are typically assessed by their final outputs, under the safety assumption that a refusal response signifies safe reasoning throughout the entire process. Challenging this assumption, our study reveals that during fake news generation, even when a model rejects a harmful request, its Chain-of-Thought (CoT) reasoning may still internally contain and propagate unsafe narratives. To analyze this phenomenon, we introduce a unified safety-analysis framework that systematically deconstructs CoT generation across model layers and evaluates the role of individual attention heads through Jacobian-based spectral metrics. Within this framework, we introduce three interpretable measures: stability, geometry, and energy to quantify how specific attention heads respond or embed deceptive reasoning patterns. Extensive experiments on multiple reasoning-oriented LLMs show that the generation risk rises significantly when the thinking mode is activated, where the critical routing decisions are concentrated in only a few contiguous mid-depth layers. By precisely identifying the attention heads responsible for this divergence, our work challenges the assumption that refusal implies safety and provides a new understanding perspective for mitigating latent reasoning risks.

Zhao Tong, Chunlin Gong, Yiping Zhang +5

Institute of Information Engineering, Chinese Academy of Sciences · School of Cyber Security, University of Chinese Academy of Sciences · Shanghai AI Laboratory +3

Language Model Safety Evaluation LLM Interpretability Text Generation Large Reasoning Models

Jan 23, 2026

Retell, Reward, Repeat: Reinforcement Learning for Narrative Theory-Informed Story Retelling

Counterfactual storytelling exposes LLM shortcomings in causal reasoning, where few-shot prompting and SFT fail to produce logical and rational narratives. This case study introduces Retell, Reward, Repeat (RRR), a narrative theory-informed RL pipeline that teaches causal story structure. We extend an existing counterfactual stories dataset with human-annotated stages of narrative equilibrium, synthesising Structuralist Narratology with scalar narrativity. An aligned LLM-as-judge automates this framework to output reward signals, teaching the policy LLM to generate texts with causal narrative structure. Evaluations show that RRR-trained 7/8B LLMs outperform few-shot and SFT baselines in logic, rationality, and completeness, also aligning with a blind human preference subset. RRR offers a linguistically grounded, cost-effective post-training mechanism for LLM storytelling using a small, query-only dataset, showing the value of integrating linguistic theories into contemporary NLP.

David Y. Liu, Xanthe Muston, Dipankar Srirag +2

University of New South Wales, Sydney, Australia

Narrative Generation Text Generation RL for Language Models Causal Reasoning in Language Models Counterfactual Reasoning in Language Models

Jan 20, 2026

Paper2Rebuttal: A Multi-Agent Framework for Transparent Author Response Assistance

Writing effective rebuttals is a high-stakes task that demands more than linguistic fluency, as it requires precise alignment between reviewer intent and manuscript details. Current solutions typically treat this as a direct-to-text generation problem, suffering from hallucination, overlooked critiques, and a lack of verifiable grounding. To address these limitations, we introduce

\textbf{RebuttalAgent}

, the first multi-agents framework that reframes rebuttal generation as an evidence-centric planning task. Our system decomposes complex feedback into atomic concerns and dynamically constructs hybrid contexts by synthesizing compressed summaries with high-fidelity text while integrating an autonomous and on-demand external search module to resolve concerns requiring outside literature. By generating an inspectable response plan before drafting,

\textbf{RebuttalAgent}

ensures that every argument is explicitly anchored in internal or external evidence. We validate our approach on the proposed

\textbf{RebuttalBench}

and demonstrate that our pipeline outperforms strong baselines in coverage, faithfulness, and strategic coherence, offering a transparent and controllable assistant for the peer review process.

Qianli Ma, Chang Guo, Zhiheng Tian +4

AutoLab, School of Artificial Intelligence, Shanghai Jiao Tong University

Multi-Agent LLM Systems LLM Hallucination Mitigation Scholarly Peer Review Agentic RAG Text Generation

Jan 19, 2026

STEP-LLM: Generating CAD STEP Models from Natural Language with Large Language Models

Computer-aided design (CAD) is vital to modern manufacturing, yet model creation remains labor-intensive and expertise-heavy. To enable non-experts to translate intuitive design intent into manufacturable artifacts, recent large language models-based text-to-CAD efforts focus on command sequences or script-based formats like CadQuery. However, these formats are kernel-dependent and lack universality for manufacturing. In contrast, the Standard for the Exchange of Product Data (STEP, ISO 10303) file is a widely adopted, neutral boundary representation (B-rep) format directly compatible with manufacturing, but its graph-structured, cross-referenced nature poses unique challenges for auto-regressive LLMs. To address this, we curate a dataset of ~40K STEP-caption pairs and introduce novel preprocessing tailored for the graph-structured format of STEP, including a depth-first search-based reserialization that linearizes cross-references while preserving locality and chain-of-thought(CoT)-style structural annotations that guide global coherence. We integrate retrieval-augmented generation to ground predictions in relevant examples for supervised fine-tuning, and refine generation quality through reinforcement learning with a specific Chamfer Distance-based geometric reward. Experiments demonstrate consistent gains of our STEP-LLM in geometric fidelity over the Text2CAD baseline, with improvements arising from multiple stages of our framework: the RAG module substantially enhances completeness and renderability, the DFS-based reserialization strengthens overall accuracy, and the RL further reduces geometric discrepancy. Both metrics and visual comparisons confirm that STEP-LLM generates shapes with higher fidelity than Text2CAD. These results show the feasibility of LLM-driven STEP model generation from natural language, showing its potential to democratize CAD design for manufacturing.

Xiangyu Shi, Junyang Ding, Xu Zhao +8

Northwestern University, Evanston, USA

Boundary Representation Modeling Text-to-CAD Generation Text Generation

Jan 13, 2026

Safe Language Generation in the Limit

Recent results in learning a language in the limit have shown that, although language identification is impossible, language generation is tractable. As this foundational area expands, we need to consider the implications of language generation in real-world settings. This work offers the first theoretical treatment of safe language generation. Building on the computational paradigm of learning in the limit, we formalize the tasks of safe language identification and generation. We prove that under this model, safe language identification is impossible, and that safe language generation is at least as hard as (vanilla) language identification, which is also impossible. Last, we discuss several intractable and tractable cases.

Antonios Anastasopoulos, Giuseppe Ateniese, Evgenios M. Kornaropoulos

Department of Computer Science George Mason University

Language Identification Text Generation

Dec 19, 2025

DEER: A Benchmark for Evaluating Deep Research Agents on Expert Report Generation

Recent advances in large language models have enabled deep research systems that generate expert-level reports through multi-step reasoning and evidence-based synthesis. However, evaluating such reports remains challenging: report quality is multifaceted, making it difficult to determine what to assess and which criteria to use; LLM-based judges may miss errors that require domain expertise to identify; and because deep research relies on retrieved evidence, report-wide claim verification is also necessary. To address these issues, we propose DEER, a benchmark for evaluating expert-level deep research reports. DEER systematizes evaluation criteria with an expert-developed taxonomy (7 dimensions, 25 subdimensions) operationalized as 101 fine-grained rubric items. We also provide task-specific Expert Evaluation Guidance to support LLM-based judging. In addition to rubric-based assessment, we propose a claim verification architecture that verifies both cited and uncited claims and quantifies evidence quality. Experiments show that current systems produce structurally plausible, evidence-citing reports, but still struggle to fully satisfy expert-level user requests and achieve logical completeness. Beyond performance comparisons, DEER makes system strengths and limitations interpretable and provides diagnostic signals for improvement.

Janghoon Han, Heegyu Kim, Changho Lee +6

LG AI Research · University of Illinois Chicago · University of Michigan, Ann Arbor

Deep Research Agents LLM Agent Evaluation AI Agent Benchmarks Text Generation

Nov 18, 2025

Tell Me: An LLM-powered Mental Well-being Assistant with RAG, Synthetic Dialogue Generation, and Agentic Planning

We present Tell Me, a mental well-being system that leverages advances in large language models to provide accessible, context-aware support for users and researchers. The system integrates three components: (i) a retrieval-augmented generation (RAG) assistant for personalized, knowledge-grounded dialogue; (ii) a synthetic client-therapist dialogue generator conditioned on client profiles to facilitate research on therapeutic language and data augmentation; and (iii) a Well-being AI crew, implemented with CrewAI, that produces weekly self-care plans and guided meditation audio. The system is designed as a reflective space for emotional processing rather than a substitute for professional therapy. It illustrates how conversational assistants can lower barriers to support, complement existing care, and broaden access to mental health resources. To address the shortage of confidential therapeutic data, we introduce synthetic client-therapist dialogue generation conditioned on client profiles. Finally, the planner demonstrates an innovative agentic workflow for dynamically adaptive, personalized self-care, bridging the limitations of static well-being tools. We describe the architecture, demonstrate its functionalities, and report evaluation of the RAG assistant in curated well-being scenarios using both automatic LLM-based judgments and a human-user study. This work highlights opportunities for interdisciplinary collaboration between NLP researchers and mental health professionals to advance responsible innovation in human-AI interaction for well-being.

Trishala Jayesh Ahalpara

Fujitsu Research of America Santa Clara, USA

Mental Health Counseling Mental Health Mental Health Conversational Agents Conversational Agents Text Generation

Oct 3, 2025

Sample, Align, Synthesize: Graph-Based Response Synthesis with ConGrs

Language models can be sampled multiple times to access the distribution underlying their responses, but existing methods cannot efficiently synthesize rich epistemic signals across different long-form responses. We introduce Consensus Graphs (ConGrs), a flexible DAG-based data structure that represents shared information, as well as semantic variation in a set of sampled LM responses to the same prompt. We construct ConGrs using a light-weight lexical sequence alignment algorithm from bioinformatics, supplemented by the targeted usage of a secondary LM judge. Further, we design task-dependent decoding methods to synthesize a single, final response from our ConGr data structure. Our experiments show that synthesizing responses from ConGrs improves factual precision on two biography generation tasks by up to 31% over an average response and reduces reliance on LM judges by more than 80% compared to other methods. We also use ConGrs for three refusal-based tasks requiring abstention on unanswerable queries and find that abstention rate is increased by up to 56%. We apply our approach to the MATH and AIME reasoning tasks and find an improvement over self-verification and majority vote baselines by up to 6 points of accuracy. We show that ConGrs provide a flexible method for capturing variation in LM responses and using the epistemic signals provided by response variation to synthesize more effective responses.

Sayan Ghosh, Shahzaib Saqib Warraich, Dhruv Tarsadiya +2

Thomas Lord Department of Computer Science, University of Southern California

Text Generation Self-Consistency in Language Models LLM Reasoning Factual Knowledge in Language Models

Sep 30, 2025

MADS: Multi-Agent Dialogue Simulation for Diverse Persuasion Data Generation

We propose MADS (Multi-Agent Dialogue Simulation), a scalable framework for generating persuasive multi-turn dialogues via agent self-play. MADS employs three coordinated agents: User Agents designed to simulate diverse persona-driven behaviors by leveraging personality signifiers such as Zodiac Signs and MBTI types, a Dialog Agent executing task-oriented persuasion strategies and an Optimization Agent evaluating and refining dialogue outcomes. We further validate its effectiveness through users' Chain-of-Attitude (CoA) modeling and dedicated LLMs' persuasion assessment. This approach enables low-cost generation of training data without human annotation, addressing key industry challenges such as lack of user data, cold-start evaluation difficulties, and prompt inefficiency. Applied to a real-world marketing scenario, MADS significantly improved the persuasion capacity of small LLMs, increasing the organic traffic conversion rate by 22.4% (from 1.83% to 2.24%) , demonstrating clear business value.

Mingjin Li, Yu Liu, Huayi Liu +4

Baidu Inc., Beijing, China

Multi-Agent LLM Systems Synthetic Data Generation LLM Agent Training Text Generation

Sep 7, 2025

Generating Individual Travel Diaries Using Large Language Models Informed by Census and Land-Use Data

This study introduces a Large Language Model (LLM) scheme for generating key attributes of travel diaries in agent-based transportation models, including purpose, mode and distance, to assess the underlying viability of LLMs for activity generation tasks. While traditional approaches rely on large quantities of proprietary household travel surveys, our method generates personas stochastically from open-source American Community Survey (ACS) and Smart Location Database (SLD) data, then synthesizes diaries through direct prompting. Our study features a novel one-to-cohort realism score: a composite of four metrics (Trip Count Score, Interval Score, Purpose Score, and Mode Score) validated against the Connecticut Statewide Transportation Study (CSTS) diaries, matched across demographic variables. Our validation utilizes Jensen-Shannon Divergence to measure distributional similarities between generated and real diaries. When compared to diaries generated with classical methods (Negative Binomial for trip generation; Multinomial Logit for mode/purpose) calibrated on the validation set, LLM generated diaries achieve comparable overall realism (LLM mean: 0.692 vs. 0.628). The LLM excels in determining trip purpose, and its trip mode predictions demonstrate greater consistency (a narrower Realism Score distribution). Meanwhile, classical models lead to better numerical estimates of trip count and activity duration. Aggregate validation confirms the LLM's statistical representativeness (LLM mean: 0.779 vs. 0.706), demonstrating LLM's zero-shot viability and establishing a quantifiable metric of diary realism for future synthetic diary evaluation systems.

Sepehr Golrokh Amin, Devin Rhoads, Fatemeh Fakhrmoosavi +2

School of Civil and Environmental Engineering, University of Connecticut, United States

Synthetic Data Generation Synthetic Data Evaluation Text Generation

Sep 4, 2025

MAGneT: Coordinated Multi-Agent Generation of Synthetic Multi-Turn Mental Health Counseling Sessions

The growing demand for scalable psychological counseling highlights the need for high-quality, privacy-compliant data, yet such data remains scarce. Here we introduce MAGneT, a novel multi-agent framework for synthetic psychological counseling session generation that decomposes counselor response generation into coordinated sub-tasks handled by specialized LLM agents, each modeling a key psychological technique. Unlike prior single-agent approaches, MAGneT better captures the structure and nuance of real counseling. We further propose a unified evaluation framework that consolidates diverse automatic metrics and expands expert assessment from four to nine counseling aspects, thus addressing inconsistencies in prior evaluation protocols. Empirically, MAGneT substantially outperforms existing methods: experts prefer MAGneT-generated sessions in 77.2% of cases on average across the nine aspects over the strongest baseline, and sessions generated by MAGneT using Llama3-8B-Instruct backbone yield 3.2% higher general counseling skills and 4.3% higher CBT-specific skills on cognitive therapy rating scale (CTRS). An open source Llama3-8B-Instruct model fine-tuned on MAGneT-generated data also outperforms models fine-tuned using baseline synthetic datasets by 6.9% on average on CTRS. We make our code, data and fine-tuned model public.

Aishik Mandal, Tanmoy Chakraborty, Iryna Gurevych

Ubiquitous Knowledge Processing Lab (UKP Lab), Department of Computer Science and Hessian Center for AI (hessian.AI), Technische Universität Darmstadt · National Research Center for Applied Cybersecurity ATHENE, Germany · Department of Electrical Engineering, Indian Institute of Technology Delhi, India +1

Mental Health Counseling Mental Health Synthetic Data Generation Multi-Agent LLMs Synthetic Data Evaluation Text Generation+1

Jun 29, 2025

From Individuals to Interactions: Benchmarking Gender Bias in Multimodal Large Language Models from the Lens of Social Relationship

Ensuring the trustworthiness of Multimodal Large Language Models (MLLMs) requires rigorous evaluation of gender bias, particularly in socially sensitive domains. Existing benchmarks primarily assess bias in isolated contexts and are less suited to capturing biases that emerge through interpersonal interactions. We introduce Genres, a benchmark for evaluating gender bias in MLLMs through the lens of social relationships in narrative generation. Grounded in Fiske's relational models theory, Genres comprises 1,440 multimodal narrative elicitation pairs spanning four fundamental relationship types, diverse social scenarios, and three age groups. Its dual-character generation tasks elicit socially situated interpersonal narratives and enable fine-grained assessment across multiple dimensions of gender bias. Experiments on six recent MLLMs reveal persistent yet strongly relationship- and model-dependent gender disparities, with some patterns becoming more pronounced in interpersonal settings. We further evaluate two complementary generation-stage mitigation strategies. Our findings demonstrate the value of relationship-aware evaluation for uncovering subtle, interaction-driven gender bias in MLLMs.

Yue Xu, Wenjie Wang

School of Information Science and Technology, ShanghaiTech University

Narrative Generation Social Bias in Language Models Language Model Bias Evaluation Multimodal Large Language Models Text Generation

Jun 16, 2025

BOW: Training Language Models to Reason Over Plausible Next Words

Next-word prediction (NWP) trains language models against a single observed continuation, even though many contexts admit multiple plausible next words. Recent RL-based next-word reasoning methods make this tension explicit: they reward a model for producing a rationale that supports one context-conditioned continuation, which can turn a pre-existing preference into a confident, self-justifying trajectory. We introduce BOW, an RL framework that instead trains models to produce self-contained, neutral, and comprehensive descriptions of the plausible next-word space. The policy generates a next-word reasoning trajectory from the full context, but a frozen scorer computes the core reward from that trajectory alone, without separately receiving the context. BOW-Reg adds a lightweight breadth regularizer to this core reward to discourage premature collapse. On two model backbones, BOW remains competitive with the original models and often outperforms trained baselines across ten general reasoning benchmarks. On benchmarks testing ambiguous references and word meanings, BOW-Reg achieves the highest SharedRef correctness and the lowest HoWN-Simple single-sense collapse on both backbones. Human evaluation further shows that BOW-Reg produces broader next-word reasoning trajectories, while direct next-word-prediction evaluation shows that these trajectories remain predictive.

Ming Shen, Zhikun Xu, Jacob Dineen +2

Arizona State University

RL for Language Model Reasoning Next-Token Prediction Language Model Post-Training Text Generation LLM Reasoning

May 31, 2025

Sarc7: Evaluating Sarcasm Detection and Generation with Seven Types and Emotion-Informed Techniques

Sarcasm is a form of humor where expressions convey meanings opposite to their literal interpretations. Classifying and generating sarcasm using large language models is vital for interpreting human communication. Sarcasm poses challenges for computational models, due to its nuanced nature. We introduce Sarc7, a benchmark that classifies 7 types of sarcasm: self-deprecating, brooding, deadpan, polite, obnoxious, raging, and manic by annotating entries of the MUStARD dataset. Classification was evaluated using zero-shot, few-shot, chain-of-thought (CoT), and a novel emotion-based prompting technique. We propose an emotion-based generation method developed by identifying key components of sarcasm-incongruity, shock value, and context dependency. Our classification experiments show that Gemini 2.5, using emotion-based prompting, outperforms other setups with an F1 score of 0.3664. Human evaluators preferred our emotion-based prompting, with 38.46% more successful generations than zero-shot prompting.

Raina Gao, Alyssa Jeong, Lang Xiong +4

Algoverse AI Research

LLM Evaluation Sarcasm Detection Text Generation

May 30, 2025

DLM-One: Diffusion Language Models for One-Step Sequence Generation

This paper introduces DLM-One, a score-distillation-based framework for one-step sequence generation with continuous diffusion language models (DLMs). DLM-One eliminates iterative refinement by aligning the scores of a student model's outputs with the score function of a pretrained teacher DLM in the forward-diffused noisy space. We demonstrate that our framework is architecture-agnostic and robust across diverse continuous manifolds, including standard token embedding spaces and logit simplex spaces. Through experiments on multiple representative DLMs, we show that DLM-One achieves up to

\sim

2000

\times

speedup in sampling steps and

\sim

500

\times

in wall-clock time, while maintaining competitive performance on benchmark text generation tasks. We further analyze failure modes in language-domain diffusion distillation and propose an adversarially-regularized two-stage training scheme to prevent student degeneration. Our findings position one-step score distillation as a viable path for the efficient deployment of continuous diffusion models operating in continuous space for natural language processing.

Tianqi Chen, Shujian Zhang, Mingyuan Zhou

The University of Texas at Austin, Austin, TX 78712, USA

Diffusion Language Models Diffusion Model Distillation Text Generation Score Distillation Sampling

May 18, 2025

Enriching Patent Claim Generation with European Patent Dataset

Drafting patent claims is time-intensive, costly, and requires professional skill. Therefore, researchers have investigated large language models (LLMs) to assist inventors in writing claims. However, existing work has largely relied on datasets from the United States Patent and Trademark Office (USPTO). To enlarge research scope regarding various jurisdictions, drafting conventions, and legal standards, we introduce EPD, a European patent dataset. EPD presents rich textual data and structured metadata to support multiple patent-related tasks, including claim generation. This dataset enriches the field in three critical aspects: (1) Jurisdictional diversity: Patents from different offices vary in legal and drafting conventions. EPD fills a critical gap by providing a benchmark of European patents to enable more comprehensive evaluation. (2) Quality improvement: EPD offers high-quality granted patents with finalized and legally approved texts, whereas others consist of patent applications that are unexamined or provisional. Experiments show that LLMs fine-tuned on EPD significantly outperform those trained on previous datasets and even GPT-4o in claim quality and cross-domain generalization. (3) Real-world simulation: We propose a difficult subset of EPD to better reflect real-world challenges. Results reveal that all tested LLMs perform substantially worse on challenging samples, which highlights the need for future research.

Lekang Jiang, Chengzu Li, Stephan Goetz

University of Cambridge

Text Generation LLM Evaluation

Mar 13, 2025

Ensemble Learning for Large Language Models in Text and Code Generation: A Survey

Generative Pretrained Transformers (GPTs) are foundational Large Language Models (LLMs) for text generation. However, individual LLMs often produce inconsistent outputs and exhibit biases, limiting their representation of diverse language patterns. The closed-source nature of many powerful LLMs further restricts industry applications due to data privacy concerns. Inspired by successes in text generation, LLM ensemble techniques are now increasingly explored for code generation. This article reviews these emerging ensemble approaches to enhance understanding, encourage further research, and promote practical implementation in both text and code generation. We categorize LLM ensembles into seven main methods - weight merging, knowledge fusion, mixture-of-experts, reward ensemble, output ensemble, routing, and cascading - analyzing capabilities of those approaches. Our findings highlight key benefits such as improved diversity representation, enhanced output quality, and greater application flexibility. These insights aid model selection for real-world tasks and crucially, lay groundwork for extending ensemble strategies to multimodal LLMs.

Mari Ashiga, Wei Jie, Fan Wu +5

School of Computing and Engineering, University of West London, London W5 5RF, United Kingdom · Turing Intelligence Technology Limited, London EC2M 2PF, United Kingdom · School of Computer Science, University of Leeds, Leeds LS2 9JT, United Kingdom

Mixture-of-Experts Language Models Language Model Ensembles LLM Code Generation Text Generation

Feb 14, 2025

Man Made Language Models? Evaluating LLMs' Perpetuation of Masculine Generics Bias

Instruct-based large language models (LLMs) have been shown to propagate and even amplify gender bias when prompted with contextually constrained instructions (e.g., writing a text from a description or selecting a gendered pronoun). However, little attention has been paid to biases in responses to contextually unconstrained (generic) instructions conveyed by gendered language, particularly masculine generics (MG). MG, found in many gender-marked languages, denote the use of the masculine gender as a supposedly neutral reference to mixed-gender groups or individuals whose gender is unknown or non-binary. Yet, psycholinguistic studies demonstrate that MG are not neutral and systematically induce gender bias. This study investigates how both local and proprietary LLMs are MG-biased when responding to generic prompts in French, examining LLMs' MG bias rates and use of gender-fair language (GFL). We create a 16k+ human noun database from existing lexical resources and evaluate six LLMs on four instruction-response datasets under two conditions: prompts with and without MG. Overall, we find that

\approx

27.57% of LLMs' responses to MG-filtered generic instructions are MG-biased (

\approx

78.55% with MG-containing prompts). Moreover, we find that LLMs rarely use GFL spontaneously. These findings highlight the persistence of MG bias in LLM outputs and models' limited tendency towards GFL strategies.

Enzo Doyen, Amalia Todirascu

University of Strasbourg

Gender Bias in Language Models Language Model Bias Evaluation Linguistic Bias in Language Models Text Generation