In recent years, the fields of natural-language processing and computational linguistics, which were revolutionized a decade ago by deep learning, were revolutionized again by large language models (LLMs). Unsurprisingly, work involving LLMs, either as a subject of inquiry themselves or as tools for other natural-language-processing applications, predominates at this year’s meeting of the North American Chapter of the Association for Computational Linguistics (NAACL). This paper guide sorts Amazon’s NAACL papers into those that deal explicitly with LLMs and those that don’t — although in many cases, the ones that don’t present general techniques or datasets that could be used with either LLMs or more-traditional models.
LLM-related work
Agents
FLAP: Flow-adhering planning with constrained decoding in LLMs
Shamik Roy, Sailik Sengupta, Daniele Bonadiman, Saab Mansour, Arshit Gupta
Attribute value extraction
EIVEN: Efficient implicit attribute value extraction using multimodal LLM
Henry Peng Zou, Gavin Yu, Ziwei Fan, Dan Bu, Han Liu, Peng Dai, Dongmei Jia, Cornelia Caragea
Continual learning
Q-Tuning: Queue-based prompt tuning for lifelong few-shot language learning
Yanhui Guo, Shaoyuan Xu, Jinmiao Fu, Jia (Kevin) Liu, Chaosheng Dong, Bryan Wang
Dialogue
Leveraging LLMs for dialogue quality measurement
Jinghan Jia, Abi Komma, Timothy Leffel, Xujun Peng, Ajay Nagesh, Tamer Soliman, Aram Galstyan, Anoop Kumar
Hallucination mitigation
Less is more for improving automatic evaluation of factual consistency
Tong Wang, Ninad Kulkarni, Yanjun (Jane) Qi
TofuEval: Evaluating hallucinations of LLMs on topic-focused dialogue summarization
Liyan Tang, Igor Shalyminov, Amy Wong, Jon Burnsky, Jake Vincent, Yu’an Yang, Siffi Singh, Song Feng, Hwanjun Song, Hang Su, Justin Sun, Yi Zhang, Saab Mansour, Kathleen McKeown
Towards improved multi-source attribution for long-form answer generation
Nilay Patel, Shivashankar Subramanian, Siddhant Garg, Pratyay Banerjee, Amita Misra
Machine translation
A preference-driven paradigm for enhanced translation with large language models
Dawei Zhu, Sony Trenous, Xiaoyu Shen, Dietrich Klakow, Bill Byrne, Eva Hasler
Natural-language processing
Toward informal language processing: Knowledge of slang in large language models
Zhewei Sun, Qian Hu, Rahul Gupta, Richard Zemel, Yang Xu
Question answering
Bring your own KG: Self-supervised program synthesis for zero-shot KGQA
Dhruv Agarwal, Rajarshi (Raj) Das, Sopan Khosla, Rashmi Gangadharaiah
Reasoning
CoMM: Collaborative multi-agent, multi-reasoning-path prompting for complex problem solving
Pei Chen, Boran Han, Shuai Zhang
Recommender systems
RecMind: Large language model powered agent for recommendation
Yancheng Wang, Ziyan Jiang, Zheng Chen, Fan Yang, Yingxue Zhou, Eunah Cho, Xing Fan, Xiaojiang Huang, Yanbin Lu, Yingzhen Yang
Reinforcement learning from human feedback
RS-DPO: A hybrid rejection sampling and direct preference optimization method for alignment of large language models
Saeed Khaki, JinJin Li, Lan Ma, Liu Yang, Prathap Ramachandra
Responsible AI
ITERALIGN: Iterative constitutional alignment of large language models
Xiusi Chen, Hongzhi Wen, Sreyashi Nag, Chen Luo, Qingyu Yin, Ruirui Li, Zheng Li, Wei Wang
MICo: Preventative detoxification of large language models through inhibition control
Roy Siegelmann, Ninareh Mehrabi, Palash Goyal, Prasoon Goyal, Lisa Bauer, Jwala Dhamala, Aram Galstyan, Rahul Gupta, Reza Ghanadan
The steerability of large language models toward data-driven personas
Junyi Li, Charith Peris, Ninareh Mehrabi, Palash Goyal, Kai-Wei Chang, Aram Galstyan, Richard Zemel, Rahul Gupta
Retrieval-augmented generation
Enhancing contextual understanding in large language models through contrastive decoding
Zheng Zhao, Emilio Monti, Jens Lehmann, Haytham Assem
Text generation
Low-cost generation and evaluation of dictionary example sentences
Bill Cai, Clarence Ng, Daniel Tan, Shelvia Hotama
Multi-review fusion-in-context
Aviv Slobodkin, Ori Shapira, Ran Levy, Ido Dagan
Vision-language models
MAGID: An automated pipeline for generating synthetic multi-modal datasets
Hossein Aboutalebi, Justin Sun, Hwanjun Song, Yusheng Xie, Arshit Gupta, Hang Su, Igor Shalyminov, Nikolaos Pappas, Siffi Singh, Saab Mansour
Prompting vision-language models for aspect-controlled generation of referring expressions
Danfeng Guo, Sanchit Agarwal, Arpit Gupta, Jiun-Yu Kao, Emre Barut, Tagyoung Chung, Jing Huang, Mohit Bansal
General and classical techniques
Conversational agents
Leveraging interesting facts to enhance user engagement with conversational interfaces
Nikhita Vedula, Giuseppe Castellucci, Eugene Agichtein, Oleg Rokhlenko, Shervin Malmasi
Information extraction
Leveraging customer feedback for multi-modal insight extraction
Sandeep Sricharan Mukku, Abinesh Kanagarajan, Pushpendu Ghosh, Chetan Aggarwal
REXEL: An end-to-end model for document-level relation extraction and entity linking
Nacime Bouziani, Shubhi Tyagi, Joseph Fisher, Jens Lehmann, Andrea Pierleoni
Machine learning
DEED: Dynamic early exit on decoder for accelerating encoder-decoder transformer models
Peng Tang, Pengkai Zhu, Tian Li, Srikar Appalaraju, Vijay Mahadevan, R. Manmatha
Machine translation
How lexical is bilingual lexicon induction?
Harsh Kohli, Helian Feng, Nicholas Dronen, Calvin McCarter, Sina Moeini, Ali Kebarighotbi
M3T: A new benchmark dataset for multi-modal document-level machine translation
Benjamin Hsu, Xiaoyu Liu, Huayang Li, Yoshinari Fujinuma, Maria Nădejde, Xing Niu, Yair Kittenplon, Ron Litman, Raghavendra Pappagari
Responsible AI
Mitigating bias for question answering models by tracking bias influence
Mingyu Derek Ma, Jiun-Yu Kao, Arpit Gupta, Yu-Hsiang Lin, Wenbo Zhao, Tagyoung Chung, Wei Wang, Kai-Wei Chang, Nanyun Peng
Semantic retrieval
Extremely efficient online query encoding for dense retrieval
Nachshon Cohen, Yaron Fairstein, Guy Kushilevitz
Text summarization
CCSUM: A large-scale and high-quality dataset for abstractive news summarization
Xiang Jiang, Markus Dreyer
Semi-supervised dialogue abstractive summarization via high-quality pseudolabel selection
Jianfeng He, Hang Su, Jason Cai, Igor Shalyminov, Hwanjun Song, Saab Mansour
Visual question answering
Multiple-question multiple-answer text-VQA
Peng Tang, Srikar Appalaraju, R. Manmatha, Yusheng Xie, Vijay Mahadevan
