News

---

Aug 27, 2024: The missing papers are now available in the Anthology. 🎉

Aug 22, 2024: The following list of the missing papers has been compiled.

Aug 20, 2024: ACL noticed that there are more than 100 accepted papers are missing from the proceedings (Announced on X).

Aug 12, 2024: The proceedings of the 62nd annual meeting of the Association for Computational Linguistics, as well as Findings: ACL and associated workshops, are now available online.

---

List of the missing papers

---

• [arXiv] DeVAn: Dense Video Annotation for Video-Language Models

• [arXiv] How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs

• [arXiv] The Heuristic Core: Understanding Subnetwork Generalization in Pretrained Language Models

• [arXiv] Multimodal ArXiv: A Dataset for Improving Scientific Comprehension of Large Vision-Language Models

• [arXiv] L-Eval: Instituting Standardized Evaluation for Long Context Language Models

• [arXiv] DIALECTBENCH: An NLP Benchmark for Dialects, Varieties, and Closely-Related Languages

• [Not Found] Causal-Guided Active Learning for Debiasing Large Language Models

• [Not Found] PsychoGAT: A Novel Psychological Measurement Paradigm through Interactive Fiction Games with LLM Agents

• [arXiv] Towards Better Understanding of Contrastive Sentence Representation Learning: A Unified Paradigm for Gradient

• [arXiv] Emergent Word Order Universals from Cognitively-Motivated Language Models

• [arXiv] Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology View

• [arXiv] MARVEL: Unlocking the Multi-Modal Capability of Dense Retrieval via Visual Module Plugin

• [arXiv] Distributional Inclusion Hypothesis and Quantifications: Probing for Hypernymy in Functional Distributional Semantics

• [arXiv] CausalGym: Benchmarking causal interpretability methods on linguistic tasks

• [arXiv] Don’t Hallucinate, Abstain: Identifying LLM Knowledge Gaps via Multi-LLM Collaboration

• [arXiv] Mission: Impossible Language Models

• [arXiv] Semisupervised Neural Proto-Language Reconstruction

• [arXiv] Speech Translation with Speech Foundation Models and Large Language Models: What is There and What is Missing?

• [arXiv] Speech vs. Transcript: Does It Matter for Human Annotators in Speech Summarization?

• [arXiv] D2LLM: Decomposed and Distilled Large Language Models for Semantic Search

• [arXiv] Arabic Diacritics in the Wild: Exploiting Opportunities for Improved Diacritization

• [arXiv] Disinformation Capabilities of Large Language Models

• [arXiv] Learn or Recall? Revisiting Incremental Learning with Pre-trained Language Models

• [arXiv] How to Handle Different Types of Out-of-Distribution Scenarios in Computational Argumentation? A Comprehensive and Fine-Grained Field Study

• [arXiv] Cendol: Open Instruction-tuned Generative Large Language Models for Indonesian Languages

• [Not Found] Must NLP be Extractive?

• [arXiv] Spiral of Silence: How is Large Language Model Killing Information Retrieval?—A Case Study on Open Domain Question Answering

• [arXiv] Latxa: An Open Language Model and Evaluation Suite for Basque

• [arXiv] Why are Sensitive Functions Hard for Transformers?

• [arXiv] Talk With Human-like Agents: Empathetic Dialogue Through Perceptible Acoustic Reception and Reaction

• [arXiv] IRCoder: Intermediate Representations Make Language Models Robust Multilingual Code Generators

• [arXiv] The Echoes of Multilinguality: Tracing Cultural Value Shifts during Language Model Fine-tuning

• [arXiv] MYTE: Morphology-Driven Byte Encoding for Better and Fairer Multilingual Language Modeling

• [arXiv] MultiLegalPile: A 689GB Multilingual Legal Corpus

• [arXiv] WebCiteS: Attributed Query-Focused Summarization on Chinese Web Search Results with Citations

• [arXiv] What Languages are Easy to Language-Model? A Perspective from Learning Probabilistic Regular Languages

• [arXiv] Tree-Averaging Algorithms for Ensemble-Based Unsupervised Discontinuous Constituency Parsing

• [arXiv] ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs

• [arXiv] ChatDev: Communicative Agents for Software Development

• [Not Found] Disentangled Learning with Synthetic Parallel Data for Text Style Transfer

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

• [arXiv] Can Large Language Models be Good Emotional Supporter? Mitigating Preference Bias on Emotional Support Conversation

• [arXiv] $\infty$Bench: Extending Long Context Evaluation Beyond 100K Tokens

• [Not Found] Natural Language Satisfiability: Exploring the Problem Distribution and Evaluating Transformer-based Language Models

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

• [arXiv] AI ‘News’ Content Farms Are Easy to Make and Hard to Detect: A Case Study in Italian

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

• [Not Found] Disambiguate Words like Composing Them: A Morphology-Informed Approach to Enhance Chinese Word Sense Disambiguation

• [arXiv] Do Llamas Work in English? On the Latent Language of Multilingual Transformers

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

• [Not Found] Media Framing: A typology and Survey of Computational Approaches Across Disciplines

• [Not Found] SPZ: A Semantic Perturbation-based Data Augmentation Method with Zonal-Mixing for Alzheimer’s Disease Detection

• [arXiv] Calibrating Large Language Models Using Their Generations Only

• [arXiv] Iterative Forward Tuning Boosts In-Context Learning in Language Models

• [arXiv] Pride and Prejudice: LLM Amplifies Self-Bias in Self-Refinement

• [arXiv] Language Complexity and Speech Recognition Accuracy: Orthographic Complexity Hurts, Phonological Complexity Doesn’t

• [arXiv] Steering Llama 2 via Contrastive Activation Addition

• [arXiv] EconAgent: Large Language Model-Empowered Agents for Simulating Macroeconomic Activities

• [arXiv] SafetyBench: Evaluating the Safety of Large Language Models

• [arXiv] Deciphering Oracle Bone Language with Diffusion Models

• [arXiv] M4LE: A Multi-Ability Multi-Range Multi-Task Multi-Domain Long-Context Evaluation Benchmark for Large Language Models

• [arXiv] RomanSetu: Efficiently unlocking multilingual capabilities of Large Language Models via Romanization

• [arXiv] Causal Estimation of Memorisation Profiles

• [arXiv] CHECKWHY: Causal Fact Verification via Argument Structure

• [arXiv] Quality-Aware Translation Models: Efficient Generation and Quality Estimation in a Single Model

• [arXiv] On Efficient and Statistical Quality Estimation for Data Annotation

• [Not Found] EZ-STANCE: A Large Dataset for English Zero-Shot Stance Detection

• [arXiv] American Sign Language Handshapes Reflect Pressures for Communicative Efficiency

• [arXiv] Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research

• [arXiv] OLMo: Accelerating the Science of Language Models

• [arXiv] Emulated Disalignment: Safety Alignment for Large Language Models May Backfire!

• [arXiv] IndicLLMSuite: A Blueprint for Creating Pre-training and Fine-Tuning Datasets for Indian Languages

• [arXiv] Reasoning in Conversation: Solving Subjective Tasks through Dialogue Simulation for Large Language Models

• [arXiv] Aya Model: An Instruction Finetuned Open-Access Multilingual Language Model

• [arXiv] BatchEval: Towards Human-like Text Evaluation

• [arXiv] ToMBench: Benchmarking Theory of Mind in Large Language Models

• [arXiv] COKE: A Cognitive Knowledge Graph for Machine Theory of Mind

• [Not Found] MultiPICo: Multilingual Perspectivist Irony Corpus

• [Not Found] AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agents

• [arXiv] MMToM-QA: Multimodal Theory of Mind Question Answering

• [arXiv] DocMath-Eval: Evaluating Math Reasoning Capabilities of LLMs in Understanding Financial Documents

• [arXiv] Unintended Impacts of LLM Alignment on Global Representation

• [arXiv] ICLEF: In-Context Learning with Expert Feedback for Explainable Style Transfer

• [arXiv] MAP’s not dead yet: Uncovering true language model modes by conditioning away degeneracy

• [Not Found] Guardians of the Machine Translation Meta-Evaluation: Sentinel Metrics Fall In!

• [Not Found] NounAtlas: Filling the Gap in Nominal Semantic Role Labeling

• [arXiv] The Earth is Flat because…: Investigating LLMs’ Belief towards Misinformation via Persuasive Conversation

• [arXiv] LooGLE: Can Long-Context Language Models Understand Long Contexts?

• [arXiv] Let’s Go Real Talk: Spoken Dialogue Model for Face-to-Face Conversation

• [arXiv] ECBD: Evidence-Centered Benchmark Design for NLP

• [arXiv] Having Beer after Prayer? Measuring Cultural Bias in Large Language Models

• [arXiv] Explicating the Implicit: Argument Detection Beyond Sentence Boundaries

• [arXiv] Word Embeddings Are Steers for Language Models

• [arXiv] Cleaner Pretraining Corpus Curation with Neural Web Scraping

• [arXiv] Linear-time Minimum Bayes Risk Decoding with Reference Aggregation

• [arXiv] What Do Dialect Speakers Want? A Survey of Attitudes Towards Language Technology for German Dialects

• [arXiv] Getting Serious about Humor: Crafting Humor Datasets with Unfunny Large Language Models

• [arXiv] Estimating the Level of Dialectness Predicts Inter-annotator Agreement in Multi-dialect Arabic Datasets

• [arXiv] Greed is All You Need: An Evaluation of Tokenizer Inference Methods

• [arXiv] Don’t Buy it! Reassessing the Ad Understanding Abilities of Contrastive Multimodal Models

• [arXiv] SeeGULL Multilingual: a Dataset of Geo-Culturally Situated Stereotypes