cs.CL · 2026-07-27 · No. 66
Computation and Language, 2026-07-27.
9 new papers in cs.CL. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
9 entries-
01
Why Large Language Models and Humans Converge and Diverge in Evaluating Creativity
Pengzhao Lyu, Yeun Joon Kim, Hanlin Xiao, Yingyue Luna Luan
cs.CL · cs.AI
Despite the growing use of large language models (LLMs) as creativity evaluators, evidence of their alignment with human evaluations remains mixed, raising the question of when and why their judgments converge with or diverge from human judgments. Across three studies and six widely used LLMs, we addressed this gap by identifying the standards underlying LLM creativity evaluation and examining their downstream implications. Study 1 showed...
-
02
From Isolated Tasks to Structured Capabilities: A Multilayer Taxonomy for Large Language Models
Shixin Fang, Jiachen Wo, Wenjuan Qin, Sihang Jiang, Yanghua Xiao
cs.CL · cs.AI
Large language model (LLM) evaluation spans diverse tasks and benchmarks, yet evidence remains organized around tasks rather than the capabilities they probe. This fragmentation limits cross-study comparison, obscures capabilities tasks recruit, and makes coverage gaps difficult to identify. We introduce a multi-layer taxonomy of 14 capability domains and 91 subskills across Primitive, Constructed, and Integrative layers. Human cognitive...
-
03
MEUSLI: a Multilingual Projector for LLM-based ASR and Beyond
Lorenzo Concina, Seraphina Fong, Marco Matassoni, Alessio Brutti
cs.CL · cs.AI · eess.AS
Lightweight projectors are an established way to connect pre-trained speech encoders with large language models (LLMs), mapping acoustic features into token-level embeddings for tasks like ASR and spoken question answering. Existing systems, however, typically only support a few languages and are often limited to English. We introduce MEUSLI, the first open-science multilingual projector family that links a Whisper encoder with open-source...
-
04
FSE: Continual Learning for Named Entity Recognition by Fast-Slow Experts
Yunan Zhang, Yang Fan, Heng Li, Xiangping Wu, Qingcai Chen
cs.CL · cs.AI
Continual Learning for Named Entity Recognition (CLNER) enable models to incrementally learn new entity types without forgetting previously acquired ones. However, existing methods suffer from catastrophic forgetting and insufficient exploitation of shared information across tasks. This paper proposes FSE, a Fast-Slow Experts enhanced span-based NER model for CLNER. The shared fast expert learns token-level links to efficiently filter out...
-
05
Benchmarking Fine-tuning and Retrieval Strategies for a Multimodal Language Model on the NRC Reactor Operator Licensing Examination
Isak Hwang, Yoon Pyo Lee
cs.CL · cs.AI
The integration of large language models (LLMs) into the nuclear power industry requires outputs grounded in domain-specific knowledge. This study evaluates a 31-billion-parameter open-weight multimodal model (Gemma 4 31B-IT) on its capacity to apply nuclear knowledge by benchmarking eight model-retrieval configurations against the U.S. Nuclear Regulatory Commission (NRC) Reactor Operator licensing examination. We evaluate 14 Generic...
-
06
J-CoT: Chain-of-Thought in J-Space
Junde Wu, Jiayuan Zhu, Fengling Liu, Minhao Hu, Jiazhen Pan
cs.CL · cs.AI
Chain-of-thought prompting improves language-model reasoning by carrying intermediate states across successive computation steps. However, relying on natural language as the only recurrent interface is overly restrictive, since many transient computations do not need to be fully verbalized. Existing latent-reasoning methods remove this constraint by recurrently propagating continuous hidden states. However, these methods pass a dense hidden...
-
07
Data Quality over Capacity: Internalizing Documents into LoRA Adapters for Closed-Book QA
Joan Figuerola Hurtado
cs.CL · cs.AI
We study baking documents directly into the weights of a 4-bit Gemma-4-e4b model via LoRA, so a system can answer questions about a corpus closed-book: no retrieval and no context-window budget. Across roughly 100 training runs from single documents to a 99-document corpus, we find that once adapter capacity is adequate, training-data quality is the dominant lever on closed-book accuracy, outweighing LoRA rank, learning rate, and two...
-
08
Khondo: A Multimodal Benchmark for Document Packet Splitting of Bangla Forms
Abu Tyeb Azad, Fahim Ahmed, Ishita Sur Apan, Ezharuddin Jubaer, Sumaiya Karim Katha, Armun Alam, Amin Ahsan Ali,...
cs.CL · cs.AI · cs.CV
Document packets, multiple documents concatenated into a single file, are common in government and administrative workflows, yet splitting them into their constituent documents is difficult, especially for low-resource languages. We introduce Khondo (Bangla for split/segment), the first benchmark for document packet splitting on Bangladeshi government forms. Unlike prior English and OCR-text-based datasets, Khondo is bilingual...
-
09
Probing Latent Colombian Identity Inferences in Qwen2.5-7B with Natural Language Autoencoders
Pablo Santiago Potes Velasco, María del Mar García Matabanchoy, Óscar Julián Pérez Ladino, Jhoan Stevan Mosquera...
cs.CL · cs.AI
Large language models may infer demographic attributes from subtle linguistic cues even when those attributes are not explicitly stated. This pilot study examines whether Qwen2.5-7B-Instruct internally represents Colombian identity, socioeconomic status, or stereotype-related information when processing Colombian-Spanish and English prompts. We use Natural Language Autoencoders (NLA) to verbalize residual-stream activations from layer 20...
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.
#D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.