cs.CL · 2026-09-22 · No. 121

Computation and Language, 2026-09-22.

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

01 — The papers

12 entries
  1. 01

    onPanda: Efficient Annotation of On-Policy Alignment Data for LLMs and Agents via Token-Level Correction

    Lei Yang, Mengyin Liu, Jia Wang, Hangyu Guo, Liang Zhao, Zheng Ge, Kang An, Binxing Jiao, Qi Han, Daxin Jiang, Siqi...

    cs.CL · cs.HC · cs.LG

    We present onPanda, an interactive tool for efficiently annotating LLM alignment data and agent trajectories. onPanda adopts token-level correction as its core interaction: while reading a model response, the annotator locates the first inappropriate token and either picks a substitute from the model's candidate tokens or types the correct text via free-form editing. The system then truncates everything after that position and continues...

    arxiv.org/abs/2609.24983 · PDF

  2. 02

    DolphinBench: Mapping the Pareto Frontier of Agent Memory

    Soumil Rathi, Deshraj Yadav, Taranjeet Singh

    cs.CL · cs.AI

    Agents today often take real-world actions that depend on long-term memory and context recall over time. However, most current memory benchmarks are built for a conversational question-answer format, where the question itself signals that some fact must be retrieved, and often which one. Moreover, benchmarks rarely require anything beyond accuracy from submissions, allowing memory systems to make unreasonable cost/time tradeoffs to achieve...

    arxiv.org/abs/2609.24971 · PDF

  3. 03

    Jev for Scientific Decisions: Evaluating Semantic Choices and Their Consequences

    Boyuan Deng, Shuyi Fan, Hongyang Zhang, Xinhong Xie

    cs.CL · cs.AI

    Scientific workflows often require choosing among known relations before a deterministic calculation can proceed. Whether observations share a culture, treatment or reference standard can change the scientific meaning of the resulting count or comparison. We evaluate Jev as a semantic decision component using a harness that follows its documented guidance and assigns arithmetic to code. The study compares twelve model configurations on twenty...

    arxiv.org/abs/2609.24965 · PDF

  4. 04

    OSWorld-Pro: Process-based Evaluation for Computer Use Agents

    Zhilin Wang, Shaokun Zhang, Yifan Zhang, Hao Zhang, Jin Xu, Binfeng Xu, Jian Hu, Yunheng Zou, Karan Sapra, Andrew...

    cs.CL · cs.AI · cs.LG

    Evaluation of Computer-Use Agents (CUAs) is often limited to the final deliverables they create (at the end of hundreds of steps) and assessed with functional verifiers, as seen in OSWorld. However, such evaluation of end-state performance lacks transparency into how and why agents fail in various tasks, obfuscating critical insight for subsequent improvement. For instance, agents that err during keyboard inputs would require a different...

    arxiv.org/abs/2609.24890 · PDF

  5. 05

    When Quantization Preserves Accuracy but Not Evidence: Explanation-Aware Post-Training Quantization for Medical LLMs

    Yeji Kim, Mi-Young Kim, Randy Goebel

    cs.CL · cs.AI

    Post-training quantization (PTQ) enables efficient deployment of large language models, and PTQ methods are usually optimized and evaluated with generic reconstruction, perplexity, or answer accuracy. But in explanation-critical domains, preserving only the final answer may be insufficient, since users may also inspect generated rationales to judge whether a prediction is trustworthy. We study this issue in medical multiple-choice question...

    arxiv.org/abs/2609.24799 · PDF

  6. 06

    Adapting Tree-Structured Speculative Decoding to DeepSeek-V4 for Efficient Inference

    Changxu Liu, Zhaogeng Li

    cs.CL · cs.AI

    Repeated execution of the target model during autoregressive decoding is a major source of LLM inference latency. Unlike linear speculation, which follows a single candidate chain, tree-structured speculation retains multiple branches from shared prefixes; under the same budget, this broader coverage can improve acceptance and efficiency. Adapting it to DeepSeek-V4 is nontrivial: its CSA/HCA online compressed attention concentrates the...

    arxiv.org/abs/2609.24698 · PDF

  7. 07

    QLoRA Fine-Tuning of Ministral LLM for Sequence-to-Function Protein Annotation

    Demian Pavlyshenko, Bohdan Pavlyshenko

    cs.CL · cs.AI · cs.NE · q-bio.QM

    Functional annotation of newly sequenced proteins remains a bottleneck in molecular biology: the number of sequences in public repositories grows far faster than the capacity for manual curation. Most computational approaches consider annotation as multi-label classification over a fixed ontology, which constrains predictions to a predefined label set. In this work we study the the protein annotation as a sequence-to-text generation problem....

    arxiv.org/abs/2609.24538 · PDF

  8. 08

    URA-NER: A Unified Retrieval-Augmented Framework with Retrieval Alignment and Uncertainty Reduction for Low-Resource NER

    Jingyu Wang, Shijie Wu, Fusheng Jin

    cs.CL · cs.AI

    In-context learning (ICL) based on large language models (LLMs) has shown promising potential in alleviating performance bottlenecks caused by the limited availability of annotated data in Named Entity Recognition (NER). However, existing methods still face issues of retrieval misalignment and generation uncertainty, making their performance heavily dependent on the LLM's capabilities. As the parameter scale of LLMs decreases, their...

    arxiv.org/abs/2609.24372 · PDF

  9. 09

    Mitigating Entity Type Confusion in Cross-Domain NER via Multidimensional Quantification and Reasoning Enhancement

    Jingyu Wang, Shijie Wu, Fusheng Jin

    cs.CL · cs.AI

    Cross-domain Named Entity Recognition (CD-NER) aims to transfer the rich knowledge in the source domain to the target domain. Recent studies adopting decomposition or generation paradigms have achieved significant performance improvements, demonstrating high accuracy in entity span detection. However, during entity type classification, models severely suffer from entity type confusion, the erroneous tendency that models classify entities of...

    arxiv.org/abs/2609.24357 · PDF

  10. 10

    Taramandal-GPT: Enhancing Astrodynamics Problem-Solving with Knowledge Retrieval and Structured Thinking

    Akhil Sharma, Jatin Gupta, Ali Imam Abidi

    cs.CL · cs.AI

    Large language models (LLMs) have shown remarkable progress in natural language understanding, yet their effectiveness in specialized fields like astronomy and astrodynamics remains limited due to challenges in multi-step reasoning, symbolic manipulation, and domain-specific terminology. To address this, we present Taramandal-GPT (Constellation-GPT), a domain-adapted framework built on the Qwen3-8b backbone, enhanced with a...

    arxiv.org/abs/2609.24246 · PDF

  11. 11

    Memory vs. Context? Influential Factors of Factual Recall in Language Models

    Guilhem Fouilhé, Nicholas Asher, Philippe Muller

    cs.CL · cs.AI

    We reproduce and stress-test the work of Yu et al. (2023), who characterize how language models (LMs) arbitrate between memorized knowledge and contradictory in-context statements. We replicate their world-capitals experiments on 31 models spanning Pythia, GPT-2, Qwen3, and Ministral families, including base and post-trained variants, and extend evaluations to five additional knowledge relation types from the ParaConflict dataset. We...

    arxiv.org/abs/2609.24238 · PDF

  12. 12

    TAC-Time: Texts as Channels For Multimodal Time Series Forecasting

    Jiayi Liang, Xiaotian Gu, Xinyu Xie, Yuanbin Wu, Xiaoling Wang

    cs.CL · cs.AI · cs.LG · cs.MM

    Most existing time series forecasting methods rely solely on numerical observations, overlooking rich contextual information from auxiliary texts. Recent multimodal approaches attempt to incorporate textual signals, but they often treat text as static features or use large language models as forecasting backbones, limiting their ability to capture temporal dynamics and increasing computational cost. To address these challenges, we propose...

    arxiv.org/abs/2609.24156 · 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.