Accepted TACL Papers

Interactive Machine Teaching by Labeling Rules and Instances
Giannis Karamanolakis Daniel Hsu Luis Gravano
Prompt Contrastive Transformation: An Enhanced Strategy for Efficient Prompt Transfer in Natural Language Processing
Shu Zhao Shiji Yang Shicheng Tan Zhen Yang Congyao Mei Zhen Duan Yanping Zhang Jie Chen
How much Semantic Information is Available in Large Language Model Tokens
David Haslett Zhenguang G. Cai
Are Triggers Needed for Document-Level Event Extraction?
Shaden Shaar Wayne Chen Maitreyi Chatterjee Barry Wang Wenting Zhao Claire Cardie
Adversarial Defence without Adversarial Defence: Enhancing Language Model Robustness via Instance-level Principal Component Removal
Yang Wang Chenghao Xiao Yizhi Li Stuart E. Middleton Noura Al Moubayed Chenghua Lin
Efficient Tuning of Large Language Models for Knowledge-Grounded Dialogue Generation
Bo Zhang Hui Ma Dailin Li Jian Ding Jian Wang Bo Xu HongFei Lin
End-to-End Long Document Summarization using Gradient Caching
Rohit Saxena Hao Tang Frank Keller
Better Slow than Sorry: Introducing Positive Friction for Reliable Dialogue Systems
Mert Inan Anthony Sicilia Suvodip Dey Vardhan Dongre Tejas Srinivasan Jesse Thomason Gökhan Tür Dilek Hakkani-Tür Malihe Alikhani
Adding Chocolate to MINT: Mitigating Metric Interference in Machine Translation
José Pombal Nuno M. Guerreiro Ricardo Rei André Martins
IssueBench: Millions of Realistic Prompts for Measuring Issue Bias in LLM Writing Assistance
Paul Rottger Musashi Hinck Valentin Hofmann Kobi Hackenburg Valentina Pyatkin Faeze Brahman Dirk Hovy
A Czech-centric Multitask and Multimetric Benchmark for Large Language Models with Duel Scoring Mechanism
Martin Fajcik Martin Dočekal Jan Doležal Karel Ondřej Karel Beneš Michal Hradiš Pavel Smrž Alexander Polok Jan Kapsa Zuzana Neverilova Aleš Horák Radoslav Sabol Michal Štefánik Adam Jirkovský David Adamczyk Petr Hyner Jan Hůla Hynek Kydlíček
Large Language Models Are Human-Like Internally
Tatsuki Kuribayashi Yohei Oseki Souhaib Ben Taieb Kentaro Inui Timothy Baldwin
TALE: Token-Adaptive Low-Rank KVCache Approximation with Reconstruction Elimination
Jaeseong Lee Seung-won Hwang Aurick Qiao Daniel Campos Zhewei Yao Yuxiong He
CRAFT Your Dataset: Task-Specific Synthetic Dataset Generation Through Corpus Retrieval and Augmentation
Ingo Ziegler Abdullatif Köksal Desmond Elliott Hinrich Schütze
MAKE: Memory-Associated Knowledge Editing
Seongsik Park Harksoo Kim Sangmin Park Jaieun Kim
Accurate and Efficient Fine-Tuning of Quantized Large Language Models Through Optimal Balance in Adaptation
Ao Shen Qiang Wang Xionglve Li Lizhi Zhang Zhiquan Lai Dongsheng Li Jiaxin Li
CRVQ: Channel-Relaxed Vector Quantization for Extreme Compression of LLMs
Yuzhuang Xu Shiyu Ji Qingfu Zhu Wanxiang Che
FoVer: First-Order Logic Verification for Natural Language Reasoning.
Pei, Yu Yongping Du Xingnan Jin
Cooking Up Creativity: A Cognitively-Inspired Approach for Enhancing LLM Creativity through Structured Representations
Moran Mizrahi Chen Shani Gabriel Stanovsky Dan Jurafsky Dafna Shahaf
Surveying the Landscape of Image Captioning Evaluation: A Comprehensive Taxonomy, Trends and Metrics Analysis
Uri Berger Gabriel Stanovsky Omri Abend Lea Frermann
QE4PE: Word-level Quality Estimation for Human Post-Editing
Gabriele Sarti Vilém Zouhar Grzegorz Chrupała Ana Guerberof-Arenas Malvina Nissim Arianna Bisazza
Generating Visual Stories with Grounded and Coreferent Characters
DANYANG LIU Mirella Lapata Frank Keller
The Impact of Automatic Speech Transcription on Speaker Attribution
Cristina Aggazzotti Matthew Wiesner Elizabeth Allyn Smith Nicholas Andrews
Safe Pruning LoRA: Robust Distance-Guided Pruning for Safety Alignment in Adaptation of LLMs
Shuang Ao Yi Dong Jinwei Hu Sarvapali Ramchurn
Active Knowledge Structuring for Large Language Models in Materials Science Text Mining
Xin Zhang Jingling Yuan Peiliang Zhang Jia Liu Lin Li
BharatBBQ: A Multilingual Bias Benchmark for Question Answering in the Indian Context
**
Overcoming Source Object Grounding for Semantic Image Editing.
Yeonjoon jung Seungtaek Choi Seung-won Hwang
The Frame Representation Hypothesis: Multi-Token LLM Interpretability and Concept-Guided Text Generation
Pedro Henrique Vaz Valois - Lincon S. Souza - Erica K. Shimomoto - Kazuhiro Fukui -
RepreGuard: Detecting LLM-Generated Text by Revealing Hidden Representation Patterns
Xin Chen Junchao Wu Shu Yang Runzhe Zhan Zeyu Wu Ziyang Luo Di Wang Min Yang Lidia S. Chao Derek F. Wong
A Unifying Scheme for Extractive Content Selection Tasks
Shmuel Amar Ori Shapira Aviv Slobodkin Ido Dagan
How to Select Datapoints for Efficient Human Evaluation of NLG Models?
Vilém Zouhar Peng Cui Mrinmaya Sachan
MultiBLiMP 1.0: A Massively Multilingual Benchmark of Linguistic Minimal Pairs
Jaap Jumelet Leonie Weissweiler Joakim Nivre Arianna Bisazza