Papers
Exploring Large Language Models’ World Perception: A Multi-Dimensional Evaluation through Data Distribution
Zhi Li, Jing Yang, Ying Liu
The Unheard Alternative: Contrastive Explanations for Speech-to-Text Models
Lina Conti, Dennis Fucci, Marco Gaido et al.
Understanding How CodeLLMs (Mis)Predict Types with Activation Steering
Francesca Lucchetti, Arjun Guha
Mechanistic Fine-tuning for In-context Learning
Hakaze Cho, Peng Luo, Mariko Kato et al.
From BERT to LLMs: Comparing and Understanding Chinese Classifier Prediction in Language Models
Ziqi Zhang, Jianfei Ma, Emmanuele Chersoni et al.
A Pipeline to Assess Merging Methods via Behavior and Internals
Yutaro Sigrist, Andreas Waldis
A Theorem-Proving-Based Evaluation of Neural Semantic Parsing
Hayate Funakura, Hyunsoo Kim, Koji Mineshima
Normative Reasoning in Large Language Models: A Comparative Benchmark from Logical and Modal Perspectives
Kentaro Ozeki, Risako Ando, Takanobu Morishita et al.
Can LLMs Detect Ambiguous Plural Reference? An Analysis of Split-Antecedent and Mereological Reference
Dang Thi Thao Anh, Rick Nouwen, Massimo Poesio
The Lookahead Limitation: Why Multi-Operand Addition is Hard for LLMs
Tanja Baeumel, Josef Van Genabith, Simon Ostermann
Circuit-Tracer: A New Library for Finding Feature Circuits
Michael Hanna, Mateusz Piotrowski, Jack Lindsey et al.
PrivacyScalpel: Enhancing LLM Privacy via Interpretable Feature Intervention with Sparse Autoencoders
Ahmed Frikha, Muhammad Reza Ar Razi, Krishna Kanth Nakka et al.
Emergent Convergence in Multi-Agent LLM Annotation
Angelina Parfenova, Alexander Denzler, Jürgen Pfeffer
Understanding the Side Effects of Rank-One Knowledge Editing
Ryosuke Takahashi, Go Kamoda, Benjamin Heinzerling et al.
When LRP Diverges from Leave-One-Out in Transformers
Weiqiu You, Siqi Zeng, Yao-Hung Hubert Tsai et al.
Investigating ReLoRA: Effects on the Learning Dynamics of Small Language Models
Yuval Weiss, David Demitri Africa, Paula Buttery et al.
Interpreting Language Models Through Concept Descriptions: A Survey
Nils Feldhus, Laura Kopf
Language Dominance in Multilingual Large Language Models
Nadav Shani, Ali Basirat
Not a nuisance but a useful heuristic: Outlier dimensions favor frequent tokens in language models
Iuri Macocco, Nora Graichen, Gemma Boleda et al.
The Comparative Trap: Pairwise Comparisons Amplifies Biased Preferences of LLM Evaluators
Hawon Jeong, ChaeHun Park, Jimin Hong et al.
Evil twins are not that evil: Qualitative insights into machine-generated prompts
Nathanaël Carraz Rakotonirina, Corentin Kervadec, Francesca Franzon et al.
Char-mander Use mBackdoor! A Study of Cross-lingual Backdoor Attacks in Multilingual LLMs
Himanshu Beniwal, Sailesh Panda, Birudugadda Srivibhav et al.
CE-Bench: Towards a Reliable Contrastive Evaluation Benchmark of Interpretability of Sparse Autoencoders
Alex Gulko, Yusen Peng, Sachin Kumar
Babies Learn to Look Ahead: Multi-Token Prediction in Small LMs
Ansar Aynetdinov, Alan Akbik