Top Conference Papers

Steering Llama 2 via Contrastive Activation Addition

Speech Translation with Speech Foundation Models and Large Language Models: What is There and What is Missing?

Same Task, More Tokens: the Impact of Input Length on the Reasoning Performance of Large Language Models

SPZ: A Semantic Perturbation-based Data Augmentation Method with Zonal-Mixing for Alzheimer's Disease Detection

Quantized Side Tuning: Fast and Memory-Efficient Tuning of Quantized Large Language Models

PsySafe: A Comprehensive Framework for Psychological-based Attack, Defense, and Evaluation of Multi-agent System Safety

Political Compass or Spinning Arrow? Towards More Meaningful Evaluations for Values and Opinions in Large Language Models

On Efficient and Statistical Quality Estimation for Data Annotation

NounAtlas: Filling the Gap in Nominal Semantic Role Labeling

Must NLP be Extractive?

MultiPICo: Multilingual Perspectivist Irony Corpus

MultiLegalPile: A 689GB Multilingual Legal Corpus

Media Framing: A Typology and Survey of Computational Approaches Across Disciplines

MMToM-QA: Multimodal Theory of Mind Question Answering

MAP's not dead yet: Uncovering true language model modes by conditioning away degeneracy

$\mathbf { M } ^ { \mathrm { 4 } } \mathbf { L E } \cdot$M4LE⋅ : A Multi-Ability Multi-Range Multi-Task Multi-Domain Long-Context Evaluation Benchmark for Large Language Models

Let's Go Real Talk: Spoken Dialogue Model for Face-to-Face Conversation

Language Complexity and Speech Recognition Accuracy: Orthographic Complexity Hurts, Phonological Complexity Doesn't

L-Eval: Instituting Standardized Evaluation for Long Context Language Models

IRCoder: Intermediate Representations Make Language Models Robust Multilingual Code Generators

Greed is All You Need: An Evaluation of Tokenizer Inference Methods

Getting Serious about Humor: Crafting Humor Datasets with Unfunny Large Language Models

G-DIG: Towards Gradient-based DIverse and hiGh-quality Instruction Data Selection for Machine Translation

Estimating the Level of Dialectness Predicts Interannotator Agreement in Multi-dialect Arabic Datasets

Emulated Disalignment: Safety Alignment for Large Language Models May Backfire!

EconAgent: Large Language Model-Empowered Agents for Simulating Macroeconomic Activities

Don't Hallucinate, Abstain: Identifying LLM Knowledge Gaps via Multi-LLM Collaboration

Do Llamas Work in English? On the Latent Language of Multilingual Transformers

CausalGym: Benchmarking causal interpretability methods on linguistic tasks