cs.CL · 2026-06-22 · No. 31
Computation and Language, 2026-06-22.
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
Your Mouse and Eyes Secretly Leak Your Preference: LLM Alignment using Implicit Feedback from Users
Haw-Shiuan Chang, Jeffrey Gomez, Mehul Patwari, Aryan Sajith, Hamed Zamani
cs.CL · cs.HC · cs.LG
To align a Large Language Model (LLM), most existing methods collect explicit human feedback and train a reward model to predict the human preference based on the response text. These existing methods have two key limitations. First, the users rarely provide explicit feedback for LLM responses, which makes the high-quality preference annotation expensive to collect. Second, the methods do not leverage implicit human feedback, which has proven...
-
02
The Register Gap: A Meaning Intelligence Framework for Nigerian Public Discourse
Celestine Achi
cs.CL · cs.AI
We introduce the Meaning Intelligence Framework (MIF), a nine-dimension annotation and evaluation schema for Nigerian public discourse that separates surface sentiment from true communicative intent. Existing benchmarks for Nigerian languages, including NaijaSenti and AfriSenti, treat sentiment classification as a three-way polarity task (positive, negative, neutral). We argue that the dominant failure mode of AI systems on Nigerian discourse...
-
03
MedRLM: Recursive Multimodal Health Intelligence for Long-Context Clinical Reasoning, Sensor-Guided Screening, Evidence-Grounded Decision Support, and Community-to-Tertiary Referral Optimization
Aueaphum Aueawatthanaphisut
cs.CL · cs.AI · cs.LG · q-bio.QM
Real-world clinical decision support requires reasoning over heterogeneous and longitudinal patient information rather than answering isolated medical questions. However, current medical large language models and retrieval-augmented generation systems often rely on single-step prompting or retrieval, which can be fragile when clinical evidence is distributed across long electronic health records, medical images, sensor streams, guidelines,...
-
04
From Texts to Scores: Tracing the Emergence of Essay Quality Representations in Large Language Models
Jiaxu Zuo, Mu You, Kaixin Lan, Tao Fang, Yujia Huo, Henghua Shen, Lidia S. Chao, Derek F. Wong
cs.CL · cs.AI
Recent advances in Large Language Models (LLMs) have substantially transformed Automated Essay Scoring (AES), yet the internal mechanisms underlying LLM-based scoring remain poorly understood. In this work, we systematically analyze the hidden representations of eight LLMs across two English essay datasets (ASAP++, CSEE) and one Portuguese dataset (ENEM). Using linear probing, cross-prompt generalization, dimensionality reduction, and...
-
05
IHUBERT: Vector-Based Semantic Deduplication and Domain-Balanced Pretraining for Persian Resources
Arash Ghafouri, Mahdi Firouzmandi, Hossein Saberi, Mohammad Reza Hasani Ahangar
cs.CL · cs.AI
Persian pretrained language models (PLMs) are still limited by the scarcity of large-scale, high-quality pretraining corpora and by insufficient evaluation beyond standard classification and NER tasks. We present IHUBERT, a monolingual Persian PLM trained from scratch with the RoBERTa-base encoder (125M parameters) on a 45 GB curated subset of the Sepahr-Danesh collection (about 7-8B tokens). To improve corpus quality and reduce redundancy,...
-
06
GEMS: Geometric Constraints Enable Multi-Semantic Superposition in LLMs
Yu Deng
cs.CL · cs.LG
Activation steering controls model behavior by modifying intermediate hidden states at inference time without retraining. Existing methods handle only single-direction injection; when multiple semantic directions are superposed without constraints, the model collapses. We show that this collapse decomposes into two independently acting sources: distributional deviation, where additive perturbations accumulate in norm across layers and drive...
-
07
Large Language Models Do Not Always Need Readable Language
Jiayi Zhu, Haoxuan Peng, Junxi Wang, Liang Ke, Chen Zhang, Linfeng Zhang
cs.CL · cs.AI
Large language models (LLMs) are commonly prompted and interfaced with human-readable natural language, even when the intended reader is another model. This paper investigates whether semantic information can be encoded in compact, non-standard textual forms that sacrifice human readability while remaining recoverable by LLMs. We refer to this class of model-centric textual representations as BabelTele, approached here not as a fixed protocol...
-
08
Prompt, Plan, Extract: Zero-Shot Agentic LLMs Workflows for Lung Pathology Extraction from Clinical Narratives
Aman Pathak, Cheng Peng, Mengxian Lyu, Ziyi Chen, Reema Solan, Sankalp Talankar, Yasir Khan, Hiren Mehta, Aokun...
cs.CL · cs.LG
Information extraction from pathology reports is essential for cancer staging, tumor registry population. Yet key data remains embedded in narrative reports, making manual extraction labor-intensive and error-prone. Traditional supervised Natural Language Processing pipelines address this through fully supervised Named Entity Recognition and Relation Extraction, but require expensive manual annotation and suffer cascading failures when...
-
09
Leverage Is Not Reach: A Control-Window Law for Single-Neuron Steering in Language Models
Hongliang Liu
cs.CL · cs.LG
Aligned language models gate behaviors such as refusal and language routing through sparse feed forward neurons, yet no theory predicts when a single neuron intervention controls a behavior coherently rather than collapsing the output. We develop a budget normalized control window framework for single neuron steering. A dose along one write direction reduces to one control coordinate: the alignment between the residual stream and the write,...
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.