Skip to yearly menu bar Skip to main content

Workshop Sat, Dec 12, 2026 • 8:00 AM – 5:00 PM AEDT MR C3.3

Workshop on the Linguistic Principles for Foundation Models

Zhiqin Yang ⋅ Yhliu ⋅ Xiuying Chen ⋅ Ekaterina Vylomova ⋅ Bo Han ⋅ Masashi Sugiyama ⋅ Jingwen Fu

[ OpenReview]

Abstract

How a task is expressed, including its wording, structure, and notation, is not merely the channel through which we query foundation models (FMs); it shapes what they can do. The same problem rendered in different but meaning-equivalent forms, whether a paraphrase, another natural language, or a formal notation such as code or logic, can shift reasoning accuracy dramatically and induce entirely different internal representations, even with model parameters held fixed. The linguistic and symbolic medium is therefore a design axis for FM capability, comparable to architecture and scale, rather than a neutral interface. This workshop establishes the principled study of this medium as a first-class research agenda, linking classical linguistic structures such as compositionality, ambiguity, tokenization, pragmatics, and typological variation to model reasoning, generalization, and alignment. It convenes machine learning researchers and linguists to advance a direction complementary to scaling: improving FMs by rethinking the media through which they perceive, reason, and act.

Chat is not available.

Schedule

Time zone: Conference local time zone

Every Time I Hire a Linguist, Inference Costs Go Down: On Linguistic Rules as Effective Prompt Compressors

Jianfei Ma ⋅ Zhaoxin Feng ⋅ Emmanuele Chersoni ⋅ Si Chen

The Capacity of In-Context Binding: a Scaling Law, a Recipe Split, and its Boundary

Manas V Sai Ravulapalli ⋅ Samrath S Chadha

Multilingual Speech Synthesis from Raw Bytes: Pronunciation, Language Identity and Code-Switching

Sumir Seth

LADS: LLM-guided Ansatz Discovery for Symbolic PDE Solutions

Seomkyun Song ⋅ Jinkyu Jeong ⋅ Jaeyong Lee

Position: Morphology, Not Frequency, Should Govern Vocabulary Allocation

Md Rashad Al Hasan Rony

Representation-Aligned Auxiliary Supervision for Language Model Adaptation

Kyuyoung Kim ⋅ Peiyao Sheng ⋅ S Ashwin Hebbar ⋅ Peiyang Xu ⋅ Yunfei Xie ⋅ Kevin Wang ⋅ Rui Xin ⋅ Chen Wei ⋅ Zhangyang "Atlas" Wang ⋅ Jinwoo Shin ⋅ Pramod Viswanath ⋅ Sewoong Oh

The Multilingual Artificial Hivemind: Do All LLMs Think Alike in Every Language?

Xaver Davey ⋅ Shubhra Mishra ⋅ Anton Adelöw ⋅ Siyao Liu

LocalTurn: Native Multi-Turn Safety Evaluation in Emirati Arabic, Bangla, Sinhala, and Yoruba

Abdullah Ibne Hanif Arean ⋅ Fatma Egal ⋅ Fathima Raihaan Ihsan ⋅ Victor T Olufemi ⋅ Naiyarah Hussain

LittleLearner: Language Models Under Pedagogically Controlled Knowledge Exposure

Fanfei Li ⋅ Jana Zeller ⋅ Manuel Prada-Corral ⋅ Thaddäus Wiedemer ⋅ Prasanna Mayilvahanan ⋅ Ryan Cotterell ⋅ Wieland Brendel

The Assistant Persona Differs Across Languages in Activation Space

Daniel Yoo ⋅ Naama Rozen ⋅ Evan Harris

Tokenization as Capacity Allocation: Matched Budgets, Communication Cuts, and Task Demand

Aditya Srivastava

Where Meaning Changes: Layerwise Trajectories of Discourse-Resolved Force

Samarth Ramesh ⋅ Manodyna K H

A Minimal-Pair Test Shows a Spectral Fork Diagnostic Tracks Prompt Surface Form

Kundana C Kommini ⋅ Kevin Zhou ⋅ Johnathan R Chen

Apparent Cross-Language Invariance Reflects Shared Identifiers in Parallel Programs

Naing Oo Lwin ⋅ Sreedhyuti Nimmagadda ⋅ Ark Dutt ⋅ Michael Ji ⋅ Randy Lim ⋅ Cole Blondin ⋅ Archana Vaidheeswaran

Adaptive Content-Contrastive Decoding for Representation-Robust Tabular Reasoning

Hanzhang Yuan ⋅ Mengxuan Hu ⋅ Daiqing Qi ⋅ vivek datla ⋅ Alfy Samuel ⋅ Sheng Li

Beyond the Word List: Context-Aware Measurement of Grievance Across Languages

LIN TIAN ⋅ Marian-Andrei Rizoiu

Evaluating Request Assumptions in Tool-Using Language Models

Sonit Sahoo

Fine-Tuning, Not Pretraining, Produces the Multilingual Geometric Split

Oumaima Hourrane

Chain-of-Thought Restructuring Does Not Reduce Sandbagging Monitorability

Joe Smith

MITRA-Swarm: Injecting Explicit Linguistic Structure into Foundation Models for Classical Machine Translation

Kayshav Bhardwaj ⋅ Pragun Seth ⋅ Kush Bhardwaj ⋅ Vijay Nagasamy ⋅ Kurt Keutzer

First-Token Broadcasters: Mechanistic Analysis of Language Identity and Distributed Robustness in Transformers

Arjun Pillai ⋅ Anjelo J Laroza ⋅ Christian Hoang

PrecisionCUA: Iterative Visual Feedback for Verifying Pixel-Precise Cursor Grounding in Code Editors

Himangi Mittal ⋅ Gaurav Mittal ⋅ Nelson D Troncoso

Beyond the Marker: Diagnosing and Mitigating Shortcut Learning in Tamil Simile Detection

Vimosh Vasanthakumar ⋅ Birunthaban Rajendram ⋅ Abishan Vasanthan

Same Task, Different Representation: Testing Robustness in Large Language Models

Ojas Patil ⋅ Pranoy Panda ⋅ Chaitanya Devaguptapu

What LLMs Know About Kyrgyz and What They Cannot Do: A Native-Authored Benchmark Separating Knowledge from Grammar

Yryskeldi Barpygulov

RAG-RST: Retrieved Exemplars as In-Context Discourse Schema for RST Parsing

Mohammadreza Sediqin ⋅ Zahra Fatemi ⋅ Shlomo Argamon

Source and Canvas Readouts Redistribute with Lexical Commitment in Masked Diffusion Language Models

Zhouyang Jin ⋅ Bo Xue ⋅ Jiaxin Ding ⋅ Luoyi Fu ⋅ Xinbing Wang

My Graph Doesn’t Help! Analyzing Causal Graph Construction, Representation, and Utility in LLMs

Aman Syed ⋅ Benjamin Li

What Is a Clarification? Estimating Model-Dependent Input Ambiguity

Jingqin Tang ⋅ Tim Tomov ⋅ Sebastian Schmidt ⋅ Dominik Fuchsgruber ⋅ Stephan Günnemann

When Semantics Survive but Symbols Go Stale: Response Conventions in Vision–Language Models

Yi H Lu ⋅ WEN-PO LIN ⋅ Bing-Siang Guo ⋅ Cheng-Fu Chou

Tree-grams : Hierarchical $n$-gram models as controlled approximators of language

Aritra Das ⋅ Francesco Cagnetta ⋅ Darshil Doshi ⋅ Victor V. Albert ⋅ Maissam Barkeshli ⋅ Andrey Gromov

Can AI Understand the Language of Origami?

Naaisha Agarwal ⋅ Yihan Wu ⋅ Xin Guan ⋅ Ayaan Garg ⋅ Yikuan Hu ⋅ Mohan Li ⋅ Vincenzo Collura ⋅ Wang-Zhou Dai ⋅ Yao-Xiang Ding ⋅ Emanuele Sansone

Zero-Compute Cross-Lingual Transferability Estimation Using Typological Feature Proxies

Dalton Harmsen ⋅ Swier Garst ⋅ Thomas van Osch ⋅ Zarè Palanciyan ⋅ Joaquin Vanschoren

When Speech Errors Break Tasks: Cross-Layer Evaluation of Conversational Voice Agents

Ancheng Deng ⋅ Yanyu Yan ⋅ Manling Li ⋅ Yimin Liu ⋅ Jin Lai

Labeled Incidence Structures: A Native Structural Interface for Foundation Models

Mahesh Godavarti

UnlearnEvo DSL: An LLM-Driven Evolutionary DSL for Machine Unlearning

jue Wang ⋅ Runyuan Zhao ⋅ Yuwang Wang ⋅ Jingwen Fu

Evolution of Cooperation in LLM Societies : A Multi-Lingual Examination

Kriti Mahajan

Triplet-Aware Sparse Higher-Order Attention for Natural Language Understanding

Mafizur Rahman ⋅ James Enouen ⋅ Yan Liu ⋅ Lijun Qian

Latent-Context Distillation: Recovering Chain-of-Thought Effect with Latent Thoughts

Sam Olesker-Taylor ⋅ Madeleine Dwyer ⋅ Erika Aranas ⋅ Luka Ribar ⋅ Michael Pearce ⋅ Luke Hudlass-Galley

Impact of Active Linguistic Streams on Visual Representational Geometry in VLMs

Sriram Y Godugula ⋅ Emmanuel Awoyemi ⋅ Frithjof Sanger ⋅ George Flint ⋅ Kevin Zhu

Grounding as a Reward: Reducing Confabulation in Natural Language Autoencoders

Seong Pyo Hong ⋅ Taejoon Eo ⋅ Hye S Lee ⋅ Daemyung Youn

Where Natural Language Ends in Agents: Executable Skill Composition with MetaSkill

Shu Meng ⋅ Wei He ⋅ Hang Zhou ⋅ Runke Liu ⋅ Kai Han ⋅ Yunhe Wang

Reading in Bands: Training-Free Causal Maps of Where Vision-Language Models Consume Compressed Context

Lakshya Narula

When Wording Changes the Control Set: Frame-Conditioned Evaluation of Instruction Interference

Nok Man Chan

Do Paired Activation Explainers Speak Plain English? Testing Faithfulness in Natural Language Autoencoders

Ananth K Suresh ⋅ Arya Hariharan

Representational Dynamics of Pragmatic Processing

Lucas Murray ⋅ Pablo Oyarzo ⋅ Cristian Buc Calderon ⋅ Andrés Contreras ⋅ Diego Vidaurre ⋅ Alvaro Soto ⋅ Edmundo Kronmüller

Whose Memory Is It? Scope-Aware Commit Rules for Long-Term LLM Memory

Hongyu Gu ⋅ Xinchang Li

What Tokens are Learned when Tokenization is Optimized Jointly with Language Modeling?

Saketh Reddy Vemula ⋅ Parameswari Krishnamurthy

System-Prompt Invariance for LLM-as-Judge Evaluation: A Linguistic Robustness Study

Uriel Benymon ⋅ Albert Ming Wei ⋅ Zhicheng Guo ⋅ Xinbei Qiu ⋅ Clara Resnick

When Typed Vocabulary Helps and When It Hurts: A Controlled Audit of Memory-Policy Routing

Yihang Chen ⋅ Pin Qian ⋅ Su Wang ⋅ Chong Peng ⋅ Huan Xu ⋅ Yiqi Sun

The Score Is Not the Structure: Brain Alignment and Cross-Lingual Transfer

saman rahbar

Test-Time Augmentation for LLMs: Where to Inject Diversity at Inference Time

Nikita Kozodoi ⋅ Zainab Afolabi ⋅ Jack Butler

When Language Rewrites the Answer Source: Typed Arbitration and Subadditive Composition in Foundation Models

Bokai Guo ⋅ Chen Fanyue ⋅ Zhizhi Wang ⋅ Jingling Wang

Output Equivalence Does Not Imply Causal Invariance in Chain-of-Thought Monitors

Joe Smith

Talk Like a Molecular Graph: Chemical Representations for Large Language Models

Nicholas Runcie ⋅ Fergus Imrie ⋅ Charlotte Deane

Training Recursive Language Models for Hierarchical Compositional Generalization

Daniil Cherniavskii ⋅ Aditya Venkatesh Marada ⋅ Andrii Zadaianchuk ⋅ Efstratios Gavves

Instruction Following with Composable Constraints

Wooseok Seo ⋅ Yoon Sangyeon ⋅ Valentina Pyatkin ⋅ Heuiyeen Yeen ⋅ Sunkyoung Kim ⋅ Yongil Kim ⋅ Youngjae Yu ⋅ Seokhee Hong

Code as the Carrier of Standing Constraints in Multi-Turn Instruction Following

Yi Zhou ⋅ Sungeun An ⋅ Chad DeLuca

High Scores, Narrow Vocabularies: Measuring Cross-Trial Diversity in Large Language Models

Alec Verdoorn ⋅ Denis Paperno

Understanding and Enhancing Conditioning Robustness of Text to Image Diffusion Models

Valery Parfenov ⋅ Timofey Belinsky ⋅ Viacheslav Vasilev ⋅ Denis Dimitrov ⋅ Aleksandr Beznosikov

Weighing What Matters: Corpus-Derived Token Importance for Language Model Objectives

Lorena Raichle ⋅ Götz-Henrik Wiegand ⋅ Tomas Hrycej ⋅ Massimo Pavone ⋅ Siegfried Handschuh

Lexical Borrowing, Code Switching, and Language State in Multilingual Foundation Models

Neil Dixit

Conversational Relevance in the Conjunction Fallacy Is Represented Independently in Language Models

Jinil Kim ⋅ Jaejun Ryu

Table Serialization Determines Which Relations Language Models Preserve

Junwei (Jeremy) Ma ⋅ Arun K Chithanar ⋅ Palash Goyal ⋅ Chul Lee

Focus On Facts: Stylistically Invariant and Factually Sensitive Text Embedding

Maximus Adeola

Escaping the Obvious: Reinforcement Learning for Conceptually Diverse Generation

Sophie Broderick ⋅ Qiawen Liu ⋅ Benjamin Eysenbach

Distinguishing among reasoning levels of GPT 5.5 Pro via a grammar lens benchmark

Emma Graham ⋅ Richard Granger

Efficient Best-Of-N with Radial Consensus Score

Manh Nguyen ⋅ Sunil Gupta ⋅ Hung Le

Grammatical and Lexical Evidence under Model Damage: A Paired Study of Hebrew, Arabic and English

Aviad Cohen

Pretraining Language Models with Subword Regularization: An Empirical Study of BPE Dropout in Low-Resource NLP

Ruan Visser ⋅ Trienko Grobler ⋅ Marcel Dunaiski

Logical subspace in LLMs

Hope Kean ⋅ Enric Boix-Adserà

Verbalizable Representations emerge before Workspace Functions in Language Models

Arjun Dabir ⋅ Ailun Shen ⋅ Michael Chan ⋅ Bangzishu Huang ⋅ Shanduojiao Jiang ⋅ Mohammed Mahfoud

Intra-Trajectory Consistency for Reward Modeling

Chaoyang Zhou ⋅ Shunyu Liu ⋅ Zengmao Wang ⋅ Di Wang ⋅ Rong-Cheng Tu ⋅ Bo Du ⋅ Dacheng Tao

Autoformalizing Chain of Thought: Representation, Verification, and Logical Shortcuts

zekun zhao ⋅ Zilong Li ⋅ Zheng Cai ⋅ Federico Ortega-Riba ⋅ Martha Palmer ⋅ James H Martin ⋅ Jeffrey Flanigan

Position: The Language of Thought Is a Design Choice, Not a Compliance Problem

Md Rashad Al Hasan Rony

Context-Grounding Gains Are Mediated by Pre-existing Machinery: Auditing GRPO, SFT, and DPO

Prakhar Gupta ⋅ Vaibhav Gupta

Instruction-Tuned Models Locally Reuse Human Syntax More Than Humans Do

Zandi Eberstadt

The Tokenization Tax: How Vietnamese Typology Exposes Vocabulary Design Failures in Open-Source LLMs

Tuan Anh Do

Diagnosing and Mitigating Script-Based Representational Divergence in Multilingual Encoders

Henry Gagnier

Weight-Space Signatures of Tokenization Cost and Morphology in Small Language Models

Rhea Senan

Iterated Integrals as Lexical Fingerprints: Path Signature Embeddings for Lexical Similarity

Raj S Singh ⋅ Pratham Agarwal

TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization

Lucheng Fu ⋅ Ye Yu ⋅ Yiyang Wang ⋅ Yiqiao Jin ⋅ Haibo Jin ⋅ B. Aditya Prakash ⋅ Haohan Wang

Beyond Structural Unification: A Perspective and Roadmap on Unified Multimodal Models

Yinyi Luo ⋅ Haoyue Bai ⋅ Yiqiao Jin ⋅ Wenyue Hua ⋅ Srijan Kumar ⋅ Marios Savvides ⋅ Qingsong Wen ⋅ Jindong Wang

Detecting Hidden Chain-of-Thought in Large Language Models with Linguistic, Behavioral, and Mechanistic Indicators

Armaan Singh ⋅ Ryan T Le ⋅ Jasmine Kaur ⋅ Edward L Lip ⋅ Kiran Nijjer ⋅ Adnan Ahmed ⋅ Vasu Sharma

Semantic Quota Constraints for Specification-Faithful Structured Generation

Himaneesh Sompalle

A Native-Reference Coordinate Geometry for L2 Pronunciation Deviation Using Self-Supervised Speech Models

Tina Raissi ⋅ Nhan Phan ⋅ Mikko Kurimo

Language Models Require Supporting Context to Predict Appropriately in Negative Contexts

James Michaelov ⋅ Benjamin Bergen

Position: Script Is the Missing Interface in Multilingual Evaluation

Md Rashad Al Hasan Rony

Shape Is Not Cardinality: Unenforced Constraints in Structured Generation

Himaneesh Sompalle

ReconSpan: Reconstruction-Guided Adaptive Latent Tokenization

Lixing Li

Predicting Response Semantics Before Generation: Identification and Causal Intervention

Mari Irikura ⋅ Naoki Nonaka ⋅ Jun Seita

HingLM: Isolating the Tokenizer's Effect for Romanized Hindi–English Code-Mixed Language

Aditya A Deshmukh ⋅ Shripad Deshmukh

Before Token Revelation: Linguistic Structure Across Denoising in Diffusion Language Models

Sai Raghuram Jandhyam ⋅ Ryan Dhalbisoi ⋅ Jennifer Seok ⋅ Daniel Huang ⋅ Justice Sefas

Following Without Understanding: Target-Blind Attention Steering Before and After Instruction Tuning

Shu Shang ⋅ Ian G Harris

Behavior Amplification: Discovering and Steering Model-Specific Reasoning Strengths in LLMs

Jingyu Wu ⋅ Neal Lawton ⋅ Alexandra Coman ⋅ Sean Wilner ⋅ Alfy Samuel ⋅ Erin Babinsky ⋅ Anoop Kumar ⋅ Daben Liu

Pre-Pre-Training Before Pixels and Genes

Seungwook Han ⋅ Dan Lee ⋅ Nathan Breslow ⋅ Mahler Revsine ⋅ Daniel Khashabi ⋅ Pulkit Agrawal

Three formal language tiers of artificial and biological intelligence

Emma Graham ⋅ Richard Granger

Talked Out of the Truth: Sycophancy in the Reasoning Chains of Multimodal Models

Mahir Numayeer Islam ⋅ Gakuto Okuyama ⋅ Nikolaus Siauw ⋅ Shivank Garg ⋅ Madhur Panwar ⋅ Vasu Sharma

Sycophancy Under Power Asymmetry in Large Language Models

Annya Dahmani ⋅ Anya Ji ⋅ Alison Gopnik ⋅ Alane Suhr

Romanian Small Language Models Trained on Native Child-Targeted Media

Radu-Stefan Popa ⋅ Adina Camelia Bleotu ⋅ Sergiu Nisioi

Output Language Confusion under Multilingual Prompt Contamination

Riju Marwah ⋅ Ritvik Garimella ⋅ Khusham Bansal ⋅ Atishay Jain ⋅ Amit Sheth

What Breaks Depth Extrapolation in Looped Language Models?

Arvindh Arun ⋅ Tianyu Zhao ⋅ Kai Arulkumaran

Do Factual Edits in LLM Embeddings Propagate Across Two Hops?

Mahdieh Mirmahdi ⋅ Yiping Ji ⋅ Zhen Zhang ⋅ Ehsan Abbasnejad

A Cross-Lingual Dissociation Between Representational Geometry and Causal Mediation

Abhijeet Gupta ⋅ Yash Kumar Sharma ⋅ Kiran Khatter ⋅ Maheshwar Dwivedy

Multilingual Rule Portability Fractures by Required Response Act: Which Directives Survive Translation, and Which Stop Binding

Anu Adesina ⋅ Aviram Berg ⋅ Ayesha Imran ⋅ Janhavi Khindkar ⋅ Maria Lomaeva ⋅ Ifeoma Okoh

Text Before Tokens: A Linguistically-Grounded, Model-Free View of Entropy in Foundation Models

Lewis Mitchell

When the Fix Becomes the Flaw: Prompt-Prefix Conditioning Induces Visual Neglect in Multimodal Video Captioning

Naishadha Badithala ⋅ Adithya R ⋅ Deepak Krishnamoorthy

Selecting Against Grammar: An Inverted Ranking of Pretraining Recipes by Downstream QA

Deep Gandhi ⋅ Ali Asaria ⋅ Tony Salomone

Emergent retokenization symmetry in large language models: phenomenology and applications

Kanishk Jain ⋅ Matthew Day ⋅ Tankut Can

Trajectories That Segment Themselves: Agent-Declared Boundaries as a Training Unit

Jingxi Wei

Conditioning Structure, Not Entropy Alone, Predicts Memorization Dynamics

Rodrigo Alvarez Lucendo ⋅ Madhur Panwar ⋅ Gail Weiss ⋅ Antoine Bosselut

Question Answering Lifecycles - A Neurosymbolic Model

Qiaoyuan Li ⋅ GABRIELLA TOM ⋅ Peter N Le

When the Gates Fire: Machine-Screened Item Construction for a Discourse-Restoration Evaluation

Maria Masood ⋅ Ankit Goyal

Model Hypnosis: Strong control of AI via additive subliminal effects

Enric Boix-Adserà ⋅ Benedict Tessler

Graph-Supervised Adaptation of CLIP Improves Relational Compositionality by Reshaping Language Embedding Geometry

Nimay Upen Shah ⋅ Amit Sethi

Who Paid for the Schema? Honest Amortized Interpolation Complexity of Reusable Reasoning Languages

Manoj Saravanan

Morphology as a Constraint on Learned Tokenization: NedoTokenizer for Turkish Foundation Models

Nedim M Sezer ⋅ Ömer F Aksoy ⋅ Ahmet R Öztürk ⋅ Feyzi A Salihoğlu ⋅ Yağız E Dalar

Position Bias Masquerades as Moral Steering in Multilingual Forced-Choice Evaluation

Sharvin Goyal ⋅ Jeremy Kalfus ⋅ Ajay Agarwal

Complementary by Coverage, Correlated by Absence: Output Representation and Complementarity in Multilingual Recognition

Anannya Umesh

Güleç: Morphology-Aware Word-Level Compilation for Efficient Turkish Language Modeling

Ahmet R Öztürk ⋅ Nedim M Sezer ⋅ Feyzi A Salihoğlu ⋅ Yağız E Dalar ⋅ Ömer F Aksoy

Better Boundary Prediction Does Not Guarantee Better Structural Representation

Michael Zhou ⋅ Markus Frohmann ⋅ Junghyun Min

Position: Linguistic Structure Reveals the Preconditions for Foundation Modeling

Alejandro Sanchez Guinea

Language Models Represent Implicit Causal Relationships

Yingshan S Wang ⋅ Jennifer Hu

Compositional Generalization via Structural Identification in a Category-Theoretic Framework

Akihiro Maeda ⋅ Thomas Seiller ⋅ Yohei Oseki

What Makes a Good Function Vector?

Minh An Pham ⋅ Anton Segeler ⋅ Thomas Wiegand ⋅ Wojciech Samek ⋅ Sebastian Lapuschkin ⋅ Patrick Kahardipraja ⋅ Reduan Achtibat

Explanation-first Explainable AI

Ryan Zhou ⋅ Ting Hu

Causal Syntax Circuits in CodeLMs: Budget and Probe Decide What Looks Localised

Harsh Kumar ⋅ Tanmay S Joshi ⋅ Rahul Maity ⋅ Anusa Saha

Accommodation or Drift? Nested Controls for Probing Conversational Adaptation in Foundation-Model Embeddings

Nishchay Nilabh ⋅ Neeraj K Sharma

The Parallax Principle: Position-Marginalized Decoding for Order-Robust Language Models

Badrinath Chandana ⋅ Ishan Jindal ⋅ Mahesh Chandran

Representation Effects Are Model-Conditional: Probing Pretrained Code Retrievers with Manim Queries

Fong S Hung

Same Answer, Different Path: Measuring Prompt Sensitivity Beyond Task Outcomes in Small Language Models

Afroditi Papadaki ⋅ Kaibang Zhang

Resource Inversion: Cross-Lingual Fidelity and Verified Deferral for Oncology Patient Communication in Low-Resource Languages

Sharvin Goyal ⋅ Sean Lee ⋅ Sunyoung Lee

How Scale Shapes Compositionality: A Case Study in Meta-Learning

Abi Tenenbaum ⋅ R. Thomas McCoy

WARDEN: Endangered Indigenous Language Transcription and Translation with 6 Hours of Training Data

Yunzhong Hou ⋅ Naijing Liu ⋅ Liang Zheng

Understood, Unaligned, or Unrouted? Three Failures Behind One Multilingual Refusal Rate

Baharak Saberidokht ⋅ Yashar Mehdad

From Structure Explicitation to Abstraction in LLM Processing of Knowledge Graphs

Max Marian ⋅ Subati Abulikemu

Rules Amortize, Pairings Don’t: Linguistic Structure Determines What Latent Task Representations Can Replace In-Context Learning

Gunmay Jhingran

Burstiness Was Measured Wrong, and Prompting Cannot Aim It

Vittoria Lanzo ⋅ Dico Angelo