EMNLP 2024 Workshop BlackBoxNLP Submissions

Does Alignment Tuning Really Break LLMs’ Internal Confidence?
Hongseok Oh, Wonseok Hwang
- Published: 21 Sept 2024, Last Modified: 06 Oct 2024
- BlackboxNLP 2024
- Readers: Everyone
How LLMs Reinforce Political Misinformation: Insights from the Analysis of False Presuppositions
Judith Sieker, Clara Lachenmaier, Sina Zarrieß
- Published: 21 Sept 2024, Last Modified: 06 Oct 2024
- BlackboxNLP 2024
- Readers: Everyone
Uncovering Syllable Constituents in the Self-Attention-Based Speech Representations of Whisper
Erfan A Shams, Iona Gessinger, Julie Carson-Berndsen
- Published: 21 Sept 2024, Last Modified: 06 Oct 2024
- BlackboxNLP 2024
- Readers: Everyone
An Adversarial Example for Direct Logit Attribution: Memory Management in GELU-4L
Jett Janiak, Can Rager, James Dao, Yeu-Tong Lau
- Published: 21 Sept 2024, Last Modified: 06 Oct 2024
- BlackboxNLP 2024
- Readers: Everyone
On the alignment of LM language generation and human language comprehension
Lena Sophia Bolliger, Patrick Haller, Lena Ann Jäger
- Published: 21 Sept 2024, Last Modified: 06 Oct 2024
- BlackboxNLP 2024
- Readers: Everyone
Transformers Learn Transition Dynamics when Trained to Predict Markov Decision Processes
Yuxi Chen, Suwei Ma, Tony Dear, Xu Chen
- Published: 21 Sept 2024, Last Modified: 06 Oct 2024
- BlackboxNLP 2024
- Readers: Everyone
Faithfulness and the Notion of Adversarial Sensitivity in NLP Explanations
Supriya Manna, Niladri Sett
- Published: 21 Sept 2024, Last Modified: 06 Oct 2024
- BlackboxNLP 2024
- Readers: Everyone
Compositional Cores: Persistent Attention Patterns in Compositionally Generalizing Subnetworks
Michael Y. Hu, Chuan Shi, Tal Linzen
- Published: 21 Sept 2024, Last Modified: 06 Oct 2024
- BlackboxNLP 2024
- Readers: Everyone
Exploring Alignment in Shared Cross-Lingual Spaces
Basel Mousi, Nadir Durrani, Fahim Dalvi, Majd Hawasly, Ahmed Abdelali
- Published: 21 Sept 2024, Last Modified: 06 Oct 2024
- BlackboxNLP 2024
- Readers: Everyone
Enhancing Question Answering on Charts Through Effective Pre-training Tasks
Ashim Gupta, Vivek Gupta, Shuo Zhang, Yujie He, Ning Zhang, Shalin Shah
- Published: 21 Sept 2024, Last Modified: 22 Oct 2024
- BlackboxNLP 2024
- Readers: Everyone
Attend First, Consolidate Later: On the Importance of Attention in Different LLM Layers
Amit Ben Artzy, Roy Schwartz
- Published: 21 Sept 2024, Last Modified: 06 Oct 2024
- BlackboxNLP 2024
- Readers: Everyone
Can We Statically Locate Knowledge in Large Language Models? Financial Domain and Toxicity Reduction Case Studies
Jordi Armengol-Estapé, Lingyu Li, Sebastian Gehrmann, Achintya Gopal, David S Rosenberg, Gideon S. Mann, Mark Dredze
- Published: 21 Sept 2024, Last Modified: 06 Oct 2024
- BlackboxNLP 2024
- Readers: Everyone
Latent Concept-based Explanation of NLP Models
Xuemin Yu, Fahim Dalvi, Nadir Durrani, Marzia Nouri, Hassan Sajjad
- Published: 21 Sept 2024, Last Modified: 06 Oct 2024
- BlackboxNLP 2024
- Readers: Everyone
MultiContrievers: Analysis of Dense Retrieval Representations
Seraphina Goldfarb-Tarrant, Pedro Rodriguez, Jane Dwivedi-Yu, Patrick Lewis
- Published: 21 Sept 2024, Last Modified: 06 Oct 2024
- BlackboxNLP 2024
- Readers: Everyone
Implicit Meta-Learning in Small Transformer Models: Insights from a Toy Task
Luan Fletcher, Victor Levoso, Kunvar Thaman, Misha Kilianovski
- Published: 21 Sept 2024, Last Modified: 06 Oct 2024
- BlackboxNLP 2024
- Readers: Everyone
Enhancing adversarial robustness in Natural Language Inference using explanations
Alexandros Koulakos, Maria Lymperaiou, Giorgos Filandrianos, Giorgos Stamou
- Published: 21 Sept 2024, Last Modified: 06 Oct 2024
- BlackboxNLP 2024
- Readers: Everyone
LLM Internal States Reveal Hallucination Risk Faced With a Query
Ziwei Ji, Delong Chen, Etsuko Ishii, Samuel Cahyawijaya, Yejin Bang, Bryan Wilie, Pascale Fung
- Published: 21 Sept 2024, Last Modified: 23 Oct 2024
- BlackboxNLP 2024
- Readers: Everyone
Language Models Linearly Represent Sentiment
Oskar John Hollinsworth, Curt Tigges, Atticus Geiger, Neel Nanda
- Published: 21 Sept 2024, Last Modified: 06 Oct 2024
- BlackboxNLP 2024
- Readers: Everyone
Inducing Induction in Llama via Linear Probe Interventions
Sheridan Feucht, Byron C Wallace, David Bau
- Published: 21 Sept 2024, Last Modified: 06 Oct 2024
- BlackboxNLP 2024
- Readers: Everyone
Learning, Forgetting, Remembering: Insights From Tracking LLM Memorization During Training
Danny D. Leybzon, Corentin Kervadec
- Published: 21 Sept 2024, Last Modified: 11 Oct 2024
- BlackboxNLP 2024
- Readers: Everyone
Competition of Mechanisms: Tracing How Language Models Handle Facts and Counterfactuals
Francesco Ortu, Zhijing Jin, Diego Doimo, Mrinmaya Sachan, Alberto Cazzaniga, Bernhard Schölkopf
- Published: 21 Sept 2024, Last Modified: 06 Oct 2024
- BlackboxNLP 2024
- Readers: Everyone
Are there identifiable structural parts in the sentence embedding whole?
Vivi Nastase, Paola Merlo
- Published: 21 Sept 2024, Last Modified: 06 Oct 2024
- BlackboxNLP 2024
- Readers: Everyone
Routing in Sparsely-gated Language Models responds to Context
Stefan Arnold, Marian Fietta, Dilara Yesilbas
- Published: 21 Sept 2024, Last Modified: 06 Oct 2024
- BlackboxNLP 2024
- Readers: Everyone
Optimal and efficient text counterfactuals using Graph Neural Networks
Dimitris Lymperopoulos, Maria Lymperaiou, Giorgos Filandrianos, Giorgos Stamou
- Published: 21 Sept 2024, Last Modified: 06 Oct 2024
- BlackboxNLP 2024
- Readers: Everyone
Fifty shapes of BLiMP: syntactic learning curves in language models are not uniform, but sometimes unruly
Bastian Bunzeck, Sina Zarrieß
- Published: 21 Sept 2024, Last Modified: 06 Oct 2024
- BlackboxNLP 2024
- Readers: Everyone