cs.CL · 2026-08-20 · No. 90

Computation and Language, 2026-08-20.

19 new papers in cs.CL. Titles, authors, abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →

01 — The papers

19 entries
  1. 01

    SPADE: Self-Play in Adaptive Synthetic Executable Environments

    Bo Liu, Simon Yu, Yiding Jiang, Ao Qu, Andrew Zhao, Zichen Liu, Junsu Kim, Zijian Zhou, Seungone Kim, Tongzheng Ren,...

    cs.CL · cs.AI

    Continuous self-improvement requires an ever-expanding pool of self-generated, diverse, adaptive goals. For language agents, existing training environment pools (hand-curated, statically synthesized, or frozen-verifier) keep the goal distribution fixed as the learner scales. We introduce SPADE (Self-Play in Adaptive Synthetic Executable Environments), a self-play RL framework in which a single LLM plays two roles: an Environment Designer that...

    arxiv.org/abs/2608.19197 · PDF

  2. 02

    DeepWeaver: Bridging the Evidence Synthesis Gap in Open-Ended Question Answering

    Xujia Wang, Yizhe Zhang, Bin Xu, Lei Hou, Juanzi Li

    cs.CL · cs.AI

    Retrieve-then-generate pipelines are commonly used to produce deep-research answers for open-ended questions, but retrieval alone is insufficient: LLMs must organize noisy and fragmented evidence into comprehensive, well-cited answers. We refer to this process as evidence synthesis. However, direct generation often underuses evidence, misaligns citations, and collapses diverse information into shallow summaries, exposing an evidence synthesis...

    arxiv.org/abs/2608.18988 · PDF

  3. 03

    MedUAG: Unified Understanding and Generation for Medical Multimodal Models

    Zijie Meng, Yuncheng Zhang, Hualiang Wang, Yitian Tang, Xiaotang Gai, Chen Shen, Songtao Jiang, Shaosheng Cao, Jian...

    cs.CL · cs.AI

    Recent Multimodal Large Language Models (MLLMs) are rapidly evolving into unified understanding and generation (UAG) frameworks. However, extending these unified paradigms to the medical domain is hindered by: the absence of comprehensive training and evaluation benchmarks, and the lack of broadly validated unified medical model. To address these gaps, we present a comprehensive foundation for medical UAG. First, we construct MedUAGCorpus,...

    arxiv.org/abs/2608.18937 · PDF

  4. 04

    Test-Time Scaling in the Wild: Why Exploitation, Not Exploration, Is the Bottleneck

    Davide Romano, Kanak Raj, Jerrod Parker, Daniele Giofrè

    cs.CL · cs.AI

    Test-time scaling (TTS) improves language model outputs by spending additional inference compute - generating multiple candidates, searching over partial sequences, or iteratively refining drafts. These techniques yield large gains on mathematics and code, but have been developed and stress-tested almost exclusively on tasks where verification is straightforward. We conduct the first compute-normalised comparison of five TTS families across...

    arxiv.org/abs/2608.18931 · PDF

  5. 05

    SMTrap: Cost-Effective DoS Attacks Against Large Reasoning Models via SMT Conflict Guidance

    Jian Yang, Zhenqi Feng, Zhaoyang Yu, Zhaoxin Fan, Kejian Wu, Xiaofeng Wang, Zheng Zhu, Jianjun Huang, Wei You, Bin Liang

    cs.CL · cs.AI

    Existing LRM-DoS methods rely heavily on model feedback to synthesize attack queries, requiring either repeated queries to the target model or training a dedicated attack model. These expensive operations severely weaken attack leverage. In this paper, we propose \emph{search amplification}, a novel, model-feedback-free LRM-DoS paradigm. It employs the conflict count derived from an Satisfiability Modulo Theories (SMT) solver as a low-cost...

    arxiv.org/abs/2608.18921 · PDF

  6. 06

    Understanding Multilingual Medical ASR Adaptation Through Layer-Wise Analysis

    Souranil Kahali, Rituparna Bose, Abner Hernandez, Tomas Arias-Vergara, Andreas Maier, Ning Ma, Paula Andrea Perez-Toro

    cs.CL · cs.AI · cs.LG · cs.SD

    Medical automatic speech recognition (MedASR) requires adaptation to specialised terminology, limited annotated clinical data, and multilingual use cases. Although large-scale pretrained ASR models such as Whisper achieve strong generalisation, their behaviour after medical and multilingual adaptation remains insufficiently understood beyond word error rate (WER). This paper investigates how multilingual medical adaptation reshapes the...

    arxiv.org/abs/2608.18825 · PDF

  7. 07

    Identifying Implicit Premises for Logical Reconstruction of Argument Graphs

    Xuyao Feng, Anthony Hunter

    cs.CL · cs.AI

    The logical reconstruction of argument graphs from natural language text is challenging because of the prevalence of enthymemes (i.e., arguments with implicit premises). There are natural language processing methods for identifying enthymemes in text, and there are symbolic methods based on abduction for identifying missing premises in a logical representation of enthymemes. However, there is a need for methods to generate implicit premises...

    arxiv.org/abs/2608.18821 · PDF

  8. 08

    Do Large Language Models Hallucinate Electric Fata Morganas?

    Kristina Šekrst

    cs.CL · cs.AI

    AI hallucinations - that is, outputs which are made up, cannot be verified, or contradict the source material - are generally regarded as an engineering flaw to be dealt with. This paper contends that they also have philosophical significance when it comes to the question of machine consciousness. We examine the known causes of hallucinations in large language models - such as source-target divergence, discrepancies between training and...

    arxiv.org/abs/2608.18816 · PDF

  9. 09

    Decomposing Wrong-Consensus Agreement in LLM Self-Consistency: A GPT-4.1 Case Study

    Lizhuo Zhang, Mengmeng Tang, Chenfeng Long, Xiaoyong Tang, Xiang Luo

    cs.CL · cs.AI

    Majority voting over multiple LLM samples is widely used to raise answer accuracy, yet its gain varies erratically: on hard questions it can even backfire. This paper gives a quantitative account of this failure. A pluralistic agreement index Gamma is defined as the expected fraction of the samples of a wrong run that agree with the consensus, normalized by a reference scale d=(1-p)/(C-1), and is decomposed into a mechanical component (what a...

    arxiv.org/abs/2608.18795 · PDF

  10. 10

    Gradient Mirage: Trainable yet Label-Unidentifiable Gradients in Large Language Model Split Learning

    Shiyu Miao, Yunlong Mao, Zirui Huang, Liang Yao, Tianshuo Zheng, Yanhui Gu, Fan Liu, Sheng Zhong

    cs.CL · cs.LG

    Gradient matching attacks (GMAs) in LLM split learning (SL) rely on a critical yet underexplored assumption: the gradient exposed at the split interface is a faithful derivative of the client's full-label training objective. This gradient-objective consistency allows a curious server to recover private labels by searching for a sequence whose induced gradient explains the observation. We propose Gradient Mirage, a defense that breaks this...

    arxiv.org/abs/2608.18767 · PDF

  11. 11

    Learning Canonical Register Automata over Ordered Data Domains

    Yong Li, Qiyi Tang, Di-De Yen

    cs.CL · cs.LG

    Register automata are finite automata equipped with memory that recognize data languages over infinite alphabets. In this work, we investigate active learning algorithms for deterministic register automata (DRAs) over ordered data domains--covering both dense domains, such as the rationals, and non-dense domains such as the integers. We show that the active learning problem for DRAs over both dense and non-dense ordered domains can be treated...

    arxiv.org/abs/2608.18765 · PDF

  12. 12

    Budget-First Tariff Recommendation (BFTR): A Complete Algorithmic Framework for Telecom Plan Recommendation without Overcharging

    Ghislain Dorian Tchuente Mondjo

    cs.CL · cs.AI

    Telecom operators traditionally offer predefined tariff grids, forcing users to choose from a limited set of plans. This paper proposes BFTR (Budget-First Tariff Recommendation), a complete algorithmic framework integrating eight Budget-First strategies, including two original hybrid approaches: Recursive Hybrid (conditional interpolation) and Knapsack-First Hybrid (priority knapsack). Unlike existing approaches that adjust prices upward to...

    arxiv.org/abs/2608.18723 · PDF

  13. 13

    MemFuse: Multi-Source Memory Fusion from Fragmented Observations

    Chao Li, Yuanfa Li, Wenhao Wu, Xule Liu, Zhi Wang, Kun Shao

    cs.CL · cs.AI

    Long-term memory is essential for agents that operate across extended interactions, yet existing memory systems and benchmarks predominantly focus on single-source textual histories. In realistic settings, however, relevant information is often fragmented across applications and devices, as well as across users and time, requiring agents to integrate dispersed observations into coherent episodic memories while preserving their source...

    arxiv.org/abs/2608.18704 · PDF

  14. 14

    Aslema at NADI 2026: Augmentation through Fewshot for SLU

    Tajwaar Shafiq, Hunzalah Hassan Bhatti, Shammur Absar Chowdhury, Firoj Alam

    cs.CL · cs.AI

    We present Aslema, our system for NADI 2026 Shared Task 5, which consists of two subtasks: intent recognition and slot filling. We evaluate four omni LLMs in a zero-shot setting and compare them with fine-tuned models. Our results show that fine-tuning consistently outperforms zero-shot inference. We further explore synthetic data augmentation by using an LLM to generate culturally grounded Tunisian Derja utterances, followed by voice cloning...

    arxiv.org/abs/2608.18689 · PDF

  15. 15

    From Storage to Access: Verifiable Activation of Parametric Knowledge in LLMs via Explicit Priming and Implicit Reasoning

    Zuocheng Ying, Yang Yang, Yumou Wu, Chuanbo Zhu, Jiarui Wang, Ziqi Wu, Jingming Cai, Junqing Yu, Zikai Song

    cs.CL · cs.AI · cs.LG

    Although Large Language Models (LLMs) encode rich factual knowledge in their parameters, reliably recalling and verifying such knowledge remains a key bottleneck in factual question answering. Existing end-to-end methods entangle knowledge elicitation with reasoning, making it difficult to determine whether correct answers arise from parametric knowledge or the input context. To address this challenge, we propose VAKE (Verifiable Activation...

    arxiv.org/abs/2608.18581 · PDF

  16. 16

    Compress and Forget: bitsandbytes Quantization Amplifies Proactive Interference in LLMs

    Shayan Shahrabi-Farahani, Dara Rahmati

    cs.CL · cs.LG

    Proactive interference (PI) is a documented failure mode in large language models in which retrieval of a repeatedly overwritten value degrades as prior overwrites accumulate, mirroring a classical phenomenon in human working memory. Post-training quantization (PTQ) is now the default deployment path for open-weight models, yet its effect on this failure mode has not been tested. We evaluate three precision levels (FP16, INT8, INT4/NF4, via...

    arxiv.org/abs/2608.18578 · PDF

  17. 17

    DART-SD: Diamond-topology Aware Retrieval and Tuning for Self-Distillation of Multi-Turn Tool-Calling Agents

    Hangrui Xu, Jiarui Wang, Yang Yang, Chuanbo Zhu, Fangda Chen, Ziqi Wu, Jingming Cai, Yan Song

    cs.CL · cs.AI · cs.LG · cs.MA

    Equipping Large Language Models (LLMs) with multi-turn tool-calling capabilities is essential for building autonomous agents. However, progress is fundamentally limited by the reliance on full-length trajectory imitation. For tasks involving multiple order-independent sub-goals, the optimal solution space forms a vast combinatorial diamond lattice. Forcing this rich topology into monolithic trajectories causes a severe topological collapse,...

    arxiv.org/abs/2608.18524 · PDF

  18. 18

    WhiteMatter: All-to-All Cross-Layer Connections via KV Mixing

    Wenbo Zhang, Xiang Ren

    cs.CL · cs.LG

    In a Transformer, each layer attends to past tokens only through KV produced at its own depth, despite the presence of deeper representations during autoregressive decoding. Feedback architectures allow shallow consumer layers to attend to KV produced by deeper past-token representations, but give all consumer layers the same fixed connection patterns to source layers. We propose WhiteMatter, which connects every attention layer to the...

    arxiv.org/abs/2608.18486 · PDF

  19. 19

    Pedagogical AI in Mental Health: A Tri-Stream Fine-Tuned LLM Framework for Automated Clinical Supervision and Risk Triage

    Shreeya Sharma, Ravish Gupta, Saket Kumar, Abhishek Aggarwal

    cs.CL · cs.AI · cs.LG

    Modern mental healthcare faces a critical shortage of senior supervisory oversight, leading to a "supervision gap" where novice therapists manage high-stakes risks with delayed professional feedback. This paper proposes a new framework utilizing a fine-tuned Mistral-7B-instruct model as an automated "Supervisor-in-the-Loop" system. By leveraging 106 sessions from the DAIC-WOZ dataset, the model performs a tri-stream analysis: (1) Therapeutic...

    arxiv.org/abs/2608.18438 · PDF

This edition is part of The Daily Abstract — cs.CL archive. Subscribe to receive these in your inbox each morning, automatically translated to Spanish, with reply-to-PDF: arxivdaily.ignorelist.com.

Colophon Set in Georgia, with system sans for interface chrome and a monospaced stack for code and paper identifiers. Sole accent: amber #D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.