cs.CL · 2026-11-05 · No. 164
Computation and Language, 2026-11-05.
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-
01
Balancing hierarchical representation and quantization: A performance trade-off in text embeddings
Kai Ponel, Marco Polignano, Erasmo Purificato, Aylin Julia Temizkan, Marco Levantesi, Giovanni Semeraro, Ernesto...
cs.CL · cs.IR · cs.LG
Hierarchical text embedding models offer variable-length representations, while quantization reduces numerical precision; both aim to improve computational efficiency. This work is an empirical benchmark study of how these two orthogonal, already-established techniques interact. We evaluate 38 tasks from the Massive Text Embedding Benchmark (MTEB) using four transformer-based embedding models, covering 1D and 2D hierarchical representations...
-
02
Ranking Agreement Does Not Reveal Paragraph-Edit Agreement in Two Released Paper Acceptance Predictors
Shaoliang Yang, Jun Wang
cs.CL · cs.LG
A fast acceptance classifier could select revisions for a slower evaluator. We ask whether agreement on existing papers supports that use. We compare a classifier of word and document features with two released text-only acceptance predictors fine-tuned from the same language model with three billion parameters. For 198 papers from the International Conference on Learning Representations, we compare model rankings of the original papers and...
-
03
Reasoning over Non-Parametric Memory in Multilingual LLMs: A Cognitive-Based Analysis of Relational Knowledge
Zohreh Abbasi Liasi, Batoul Hammoud, Anas Madkoor, Ehsaneddin Asgari
cs.CL · cs.AI
Retrieval-augmented generation (RAG) assumes that language models can reason over relations stated in their context rather than fall back on associations memorized during pretraining. We study this evidence-conditioned relational reasoning in isolation, with the facts supplied directly in the prompt rather than retrieved. \textsc{Rel-Bloom} is a controlled multilingual diagnostic of 450 multiple-choice questions built from 30 Wikidata...
-
04
ALTO: African and Levantine Tech-Facilitated Gender-Based Violence Corpus
Tianwei Zhang, Ivy Njoki Nyagwencha, Zahraa Dirani, Shalini Joshi, Scott A. Hale
cs.CL · cs.AI · cs.CY · cs.LG
Tech-facilitated gender based violence (TFGBV) is a pervasive online harm affecting women and gender minority groups through its many direct and covert forms. Current models and annotated datasets for gendered harm detection are dominated by data from, and models trained in, Global North languages. In collaboration with civil society organizations (CSOs) from Jordan, Francophone West Africa, and Kenya, we developed a community-led approach to...
-
05
NaijaFacts: A Framework for Disentangling Language from Knowledge in Facts about Nigeria
Zainab Afolabi, Nikita Kozodoi, Jack Butler, Babs Khalidson
cs.CL · cs.AI · cs.LG
Multilingual benchmarks for African languages mostly translate generic questions into local languages, measuring linguistic competence but not whether models know facts about Africa. We introduce \naija, a benchmark of factual and statistical questions about Nigeria, authored by native speakers and grounded in authoritative official statistics, with every question available in English, Nigerian Pidgin, \yoruba, Igbo, and Hausa. Answering...
-
06
ArcRAG: Agentic Compositional Retrieval over Knowledge Graphs
Jyotin Goel, Abhinav Arun, Tejas Prakash Agarwal, Bhaskarjit Sarmah, Stefano Pasquali
cs.CL · cs.AI · cs.IR
Graph-based retrieval-augmented generation (GraphRAG) answers questions by retrieving over a knowledge graph built from a corpus. Yet retrieval strategies are designed around the structure their own construction pipeline produces, and whether they survive a change of construction is rarely tested. We study this cross-construction portability: whether one retrieval procedure, with no construction-specific schema, relation names, or retuning,...
-
07
Mass Producing Training Data with Surprising Side Effects
Yaowen Ye, Jacob Steinhardt, Sarah Schwettmann, Cassidy Laidlaw
cs.CL · cs.AI · cs.LG
Training data can have unexpected side effects on language model behavior outside the training domain: insecure code data can induce broad misalignment, and outdated bird names can induce a 19th-century persona. Understanding such generalization is hard because only dozens of isolated examples exist, each constructed by hand or discovered by accident. We propose automatically discovering such datasets with surprising side effects (DSSEs). We...
-
08
Zuse: A Decision Model for European Languages
Umair Mehmood Imam
cs.CL · cs.LG
Decision models read a document and return a probability for each of a fixed set of options instead of generating text. Several appeared in 2026, but none has published results outside English. We describe Zuse, three decision models (4B, 9B and 27B) that train a low-rank adapter and a pointer head on frozen open-weight bases, targeting 27 European languages, and use them to study how this design behaves across languages and tasks. On a broad...
-
09
Loop Before You Leap: What Recurrent Depth Can and Cannot Buy in Data-Limited Pretraining
Daichi Hotta, Yohei Kobashi, Takeshi Kojima, Yusuke Iwasawa, Yutaka Matsuo
cs.CL · cs.LG
Multimodal models have often scored below text-only baselines in the BabyLM Challenge (Klerings et al., 2024; Takmaz et al., 2025). We test whether additional recurrent computation helps close this gap. Recurrence increases computation by reusing layers without adding parameters or training data. Using a single implementation, we compare standard and looped Transformers under a 100M-word budget, with three seeds per main condition. Each image...
-
10
Editing Large Language Models with Geometry-Aware Regularization
Bingqing Liu, Wei Liu, Jun Wang, Xiaobo Sun, Yuhua Li, Ruixuan Li
cs.CL · cs.AI
Knowledge editing has become a key technique for updating knowledge in large language models. However, existing methods neglect the geometric structure of the knowledge representation space, leading to two key limitations: they cannot distinguish which pre-trained knowledge should be preferentially preserved (core vs. non-core) nor which new edits are inherently difficult (hard vs. easy). To address this, we propose GEdit, a geometry-aware...
-
11
AssameseLM-E2B: An Open-Weight Assamese Language Model for Efficient Consumer-Grade Deployment
Pragyan Phukan
cs.CL · cs.AI · cs.LG
While Large Language Models (LLMs) excel in high-resource languages, their performance often degrades in low-resource languages due to tokenization inefficiencies, generative instability, and linguistic interference. This paper presents AssameseLM-E2B and its instruction-tuned variant, AssameseLM-E2B-it, a 2-billion-parameter model adapted specifically for low resource Assamese language. Built upon the Gemma-4 architecture, the model...
-
12
The Harness Is the Model: Agent Scaffolding Changes a Fixed LLM's Compliance with Banking Conduct Rules, Unevenly Across Models
Mehmet Murat Huyut
cs.CL · cs.AI · cs.CY
Banks validate language models, but they deploy systems: a model inside a harness that decides what it sees, which tools it can call and who checks its actions. We test whether that harness changes compliance with banking conduct rules when the model is held fixed. Four open-weight models each ran five harnesses (a pipeline that makes one structured decision, a ReAct-style tool loop, a loop in which the policy is reachable only through...
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.