cs.CL · 2026-07-09 · No. 48
Computation and Language, 2026-07-09.
15 new papers in cs.CL. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
15 entries-
01
Accurate, Interdisciplinary and Transparent Structure-property Understanding with Deep Native Structural Reasoning
Chen Tang, Yizhou Wang, Jianyu Wu, Lintao Wang, Shixiang Tang, Pengze Li, Encheng Su, Jun Yao, Jiabei Xiao, Yuqi...
cs.CL · cs.AI · cs.CE · cs.LG
Structure-property relationships are foundational to biology, chemistry and materials science, where function, reactivity and physical response emerge from spatial, chemical and periodic organization. Mechanistically explaining these relationships requires interpreting structural evidence through scientific principles and physical constraints, from stereochemistry and bonding to symmetry, energetics and periodic order. However, applying...
-
02
Co-LMLM: Continuous-Query Limited Memory Language Models
Yair Feldman, Linxi Zhao, Nathan Godey, Dongyoung Go, Yilun Hua, Kilian Q. Weinberger, Jennifer J. Sun, Yoav Artzi
cs.CL · cs.AI · cs.LG
Limited memory language models (LMLMs) externalize factual knowledge during pretraining to a knowledge base (KB), rather than memorizing it in their weights. During generation, the model then fetches knowledge from the KB as needed. This recently introduced paradigm provides multiple advantages, including knowledge control capabilities that remain beyond conventional LLMs. We propose continuous-query LMLM (CO-LMLM), where the KB pairs...
-
03
Does Bielik Know What It Doesn't Know? Activation Dispersion Separates Entity Familiarity from Factual Reliability Across Model Scale
Grzegorz Brzezinka
cs.CL · cs.LG
Large language models hallucinate most about entities they have never seen. We ask whether a model's activations betray entity familiarity before a single answer token is generated, and whether that signal predicts the factual reliability of the answers. On four Polish Bielik models (1.5B-11B parameters), we probe four entity domains (athletes, cities, writers, musicians), each with 42 well-known, 42 obscure-but-real, and 42 fabricated...
-
04
DiaLLM: An Investigation into the Robustness-Generation Gap in English Dialect Adaptation
Jordan Painter, Dipankar Srirag, Adarsh Kappiyath, Diptesh Kanojia, Aditya Joshi, Lu Yin
cs.CL · cs.AI
Large language models increasingly \emph{understand} dialectal English, yet still \emph{produce} only standard, US-leaning English, leaving dialectal generation, the harder half of the problem, largely unaddressed. We introduce \textbf{DiaLLM}, which continually pretrains three open-weight language model families on the International Corpus of English and applies implicit and explicit post-training paradigms, each combined with three model...
-
05
Future Confidence Distillation in Large Language Models
Sahil Kale
cs.CL · cs.AI
Reliable confidence estimation is essential for deploying large language models (LLMs) in confidence-aware systems, where downstream decisions such as retrieval, tool use, and adaptive computation depend on accurately estimating answer reliability. Existing approaches, however, largely treat confidence as a property of completed responses, overlooking how confidence-related information evolves throughout the answering process. In this work,...
-
06
PALS: Percentile-Aware Layerwise Sparsity for LLM Pruning
Yazdan Jamshidi, Alexey Shvets
cs.CL · cs.LG
One-shot pruning methods like Wanda and SparseGPT apply the same sparsity ratio to every layer of a transformer, ignoring known variation in layer importance. We propose PALS (Percentile-Aware Layerwise Sparsity), which adjusts per-layer sparsity based on the 99th percentile of activation magnitudes, bounded to $\pm 5\%$ around the target ratio. On LLaMA-2-7B at 50\% sparsity, PALS achieves 10.96 WikiText-2 perplexity versus 12.92 for uniform...
-
07
SynthAVE: Scalable Synthetic Labeling for E-Commerce with LLM-Arena Validation
Andrea Scarinci, Virginia Negri, Brayan Impata, Suleiman Khan, Victor Martinez, Marcello Federico
cs.CL · cs.AI
Fine-tuning large language models (LLMs) for e-commerce attribute extraction requires labeled data representative across thousands of product types, attributes, and multiple languages. This combinatorial scale translates to millions of annotations, rendering human labeling prohibitively costly. While recent work has demonstrated synthetic label generation using LLMs, deploying such approaches at industrial scale requires integrated quality...
-
08
TF-Engram: A Train-Free Engram with SSD-Backed Memory for Large Language Models
Yutang Ma, Kecheng Huang, Xikun Jiang, Zili Shao
cs.CL · cs.LG
Large Language Models (LLMs) store factual knowledge and domain-specific patterns implicitly in dense Transformer parameters, making knowledge expansion costly through pretraining, fine-tuning, retrieval augmentation, or longer contexts. Engram-style memory offers a compact hidden-state injection pathway, but existing GPU-resident designs often rely on hash-based compression, causing unrelated phrases to collide in shared slots and weakening...
-
09
R^3: Advertisement Compliance Rectification via Group-Relative Experience Extractor and Curriculum Reinforcement
Yuan Chen, Zhenyu Hu, Mengge Xue, Te Cao, Liqun Liu, Peng Shu, Huan Yu, Jie Jiang
cs.CL · cs.LG
Rigorous content moderation is crucial for online advertising but leads to millions of daily rejections. This scale renders manual rectification infeasible, particularly for video advertisements. However, existing safety-driven methods often suffer from aggressive over-editing, which compromises the advertiser's original semantic intent merely to satisfy compliance. In this work, we target the rectification of textual violations in video ads,...
-
10
Behavior Leverage Imbalance in Multi-Teacher On-Policy Distillation
Jiabin Shen, Guang Chen, Chengjun Mao
cs.CL · cs.LG
Agentic language models must learn when to call tools, when to consume tool responses, and when to answer directly. This makes multi-teacher on-policy distillation a natural training strategy: one teacher can specialize in tool calls, another in direct responses, and the student can learn from both on its own generated distribution. We show that this strategy can induce a behavior shift that is invisible from aggregate losses alone. In a...
-
11
Riemannian Geometry for Pre-trained Language Model Embeddings
Szczepan Konior, Alexandre Quemy, Przemysław Klocek, Grégoire Cattan, Bartłomiej Sobieski
cs.CL · cs.AI
Understanding the geometric structure of pre-trained language model embeddings matters for interpretability and safety. We ask whether sentence-level classification signal lives in the Riemannian geometry of contextual token embeddings, and probe it by extracting per-token pullback metrics from a learned encoder's analytical Jacobian and aggregating them with the Fréchet mean on the symmetric positive definite (SPD) manifold; we call this...
-
12
MILES: Modular Instruction Memory with Learnable Selection for Self-Improving LLM Reasoning
Ruilin Tong, Dong Gong
cs.CL · cs.LG
Large language models (LLMs) increasingly improve their reasoning at test time via additional computation, yet most existing works treat each problem in isolation. When problems arrive sequentially, accumulating reusable experience across them can further improve performance. Existing memory-based methods either store whole-solution templates that generalize poorly to novel problems or use heuristic step-level selection that is not optimized...
-
13
Comprehensive Evaluation of Large Language Model Responses: A Multi-Factor Scoring System
Yiming Gai, Junde Lu, Xuefei Huang
cs.CL · cs.AI
The remarkable performance of large language models (LLMs) in linguistic tasks underscores an urgent need for comprehensive evaluation of their response quality. Prevailing methods, often confined to singular dimensions, fall short of capturing the full spectrum of model capabilities. This study introduces a multifactor scoring paradigm, integrating accuracy, conciseness, factual consistency, readability, and coherence, complemented by a...
-
14
Gradient-Based Speech-to-Text Alignment for Any ASR Model: From CTC to Speech LLMs
Albert Zeyer, Ralf Schlüter, Hermann Ney
cs.CL · cs.AI · cs.CV · cs.LG
Speech-to-text alignment means finding the temporal boundaries of each word in the audio. Some models provide such an alignment directly and others do not. Connectionist temporal classification (CTC) and transducer models have an alignment by construction, whereas attention-based encoder-decoders (AED) and speech large language models (LLMs) do not, and their word timings are usually read off the attention weights instead. All of these...
-
15
Ad Headline Generation using Self-Critical Masked Language Model
Yashal Shakti Kanungo, Sumit Negi, Aruna Rajan
cs.CL · cs.AI · cs.LG
For any E-commerce website it is a nontrivial problem to build enduring advertisements that attract shoppers. It is hard to pass the creative quality bar of the website, especially at a large scale. We thus propose a programmatic solution to generate product advertising headlines using retail content. We propose a state of the art application of Reinforcement Learning (RL) Policy gradient methods on Transformer based Masked Language Models....
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.