Papers by Simeng Sun
PEARL: Prompting Large Language Models to Plan and Execute Actions Over Long Documents (2024.eacl-long)
Copied to clipboard
| Challenge: | Using chain-of-thought prompting, large language models perform better on complex reasoning tasks. |
| Approach: | They propose a prompting framework that decomposes a question into a sequence of actions and executes them over the document to obtain the answer. |
| Outcome: | The proposed framework outperforms zero-shot and chain-of-thought prompting on a QuALITY dataset . it proposes a plan based on actions mined from a training set and executes it step by step . |
FOLIO: Natural Language Reasoning with First-Order Logic (2024.emnlp-main)
Copied to clipboard
Simeng Han, Hailey Schoelkopf, Yilun Zhao, Zhenting Qi, Martin Riddell, Wenfei Zhou, James Coady, David Peng, Yujie Qiao, Luke Benson, Lucy Sun, Alexander Wardle-Solano, Hannah Szabó, Ekaterina Zubova, Matthew Burtell, Jonathan Fan, Yixin Liu, Brian Wong, Malcolm Sailor, Ansong Ni, Linyong Nan, Jungo Kasai, Tao Yu, Rui Zhang, Alexander Fabbri, Wojciech Kryscinski, Semih Yavuz, Ye Liu, Xi Lin, Shafiq Joty, Yingbo Zhou, Caiming Xiong, Rex Ying, Arman Cohan, Dragomir Radev
| Challenge: | Existing benchmarks for logical reasoning in large language models lack language naturalness or limited complexity. |
| Approach: | They propose to use first-order logic annotations to evaluate logical reasoning capabilities of large language models. |
| Outcome: | The proposed dataset evaluates the FOL reasoning ability of supervised fine-tuning on medium-sized language models. |
ChapterBreak: A Challenge Dataset for Long-Range Language Models (2022.naacl-main)
Copied to clipboard
| Challenge: | Existing long-range language models lack a meaningful evaluation of their discourse-level language understanding capabilities. |
| Approach: | They propose a dataset that provides an LRLM with a long segment from a narrative that ends at a chapter boundary and asks it to distinguish the beginning of the ground-truth next chapter from n-token segments. |
| Outcome: | The proposed dataset shows that existing models fail to leverage long-range context . |
SWAN: An Efficient and Scalable Approach for Long-Context Language Modeling (2025.emnlp-main)
Copied to clipboard
Krishna C Puvvada, Faisal Ladhak, Santiago Akle Serano, Cheng-Ping Hsieh, Shantanu Acharya, Somshubra Majumdar, Fei Jia, Samuel Kriman, Simeng Sun, Dima Rekesh, Boris Ginsburg
| Challenge: | Existing decoder-only models struggle with context lengths beyond their training distribution. |
| Approach: | They propose a causal Transformer architecture that generalizes robustly to sequence lengths longer than seen during training. |
| Outcome: | The proposed decoder-only architecture can generalize robustly to longer contexts . it is more computationally efficient than the standard Transformer architecture, the authors say . |
Alternative Input Signals Ease Transfer in Multilingual Machine Translation (2022.acl-long)
Copied to clipboard
| Challenge: | Recent work in multilingual machine translation (MMT) has focused on the potential of positive transfer between languages. |
| Approach: | They propose to augment training data with alternative signals that unify different writing systems, such as phonetic, romanized, and transliterated input. |
| Outcome: | The proposed model outperforms strong ensemble baselines on Indic and Turkic languages by 1.3 BLEU points on both languages. |
Do Long-Range Language Models Actually Use Long-Range Context? (2021.emnlp-main)
Copied to clipboard
| Challenge: | Language models are generally trained on short, truncated input sequences, which limits their ability to use discourse-level information present in long-range context to improve their predictions. |
| Approach: | They analyze two long-range Transformer language models that accept 8K token inputs . they find that providing long-term context only improves their predictions on a small set of tokens - not sentence-level ones . |
| Outcome: | The proposed model improves on PG-19 with only 2K tokens and does not help at all for sentence-level prediction tasks. |
TopicGPT: A Prompt-based Topic Modeling Framework (2024.naacl-long)
Copied to clipboard
| Challenge: | TopicGPT uses large language models to uncover latent topics in text . topic models represent topics as bags of words that require "reading the tea leaves" topic models also offer limited control over formatting and specificity of topics . |
| Approach: | TopicGPT uses large language models to uncover latent topics in text . authors propose a prompt-based framework that produces topics that align better with human categorizations . |
| Outcome: | TopicGPT produces topics that align better with human categorizations compared to competing methods. |
How much do contextualized representations encode long-range context? (2025.findings-naacl)
Copied to clipboard
| Challenge: | Existing studies of contextualized representations focus on short sequences of tens to hundreds of tokens, whereas modern language models handle hundreds of thousands of token in a single context window. |
| Approach: | They use a perturbation setup and a metric to capture contextualization of long-range patterns from the perspective of representation geometry. |
| Outcome: | The proposed model can encode long-range contexts, but it's not fully recurrent, the authors say . their results suggest improvements in existing language models . |
IGA: An Intent-Guided Authoring Assistant (2021.emnlp-main)
Copied to clipboard
Simeng Sun, Wenlong Zhao, Varun Manjunatha, Rajiv Jain, Vlad Morariu, Franck Dernoncourt, Balaji Vasan Srinivasan, Mohit Iyyer
| Challenge: | Pretrained language models have improved writing assistance functions such as autocomplete, but more complex and controllable writing assistants have yet to be explored. |
| Approach: | They build an intent-guided authoring assistant that follows fine-grained author directives by specifying different writing intents. |
| Outcome: | The proposed system generates output satisfying the author's intent and can be rephrased to their liking. |
Hard-Coded Gaussian Attention for Neural Machine Translation (2020.acl-main)
Copied to clipboard
| Challenge: | Recent work has questioned the importance of multi-headed attention in achieving high translation quality. |
| Approach: | They develop a “hard-coded” attention variant without any learned parameters. |
| Outcome: | The proposed model reduces BLEU scores by adding a single learned cross attention head to an otherwise hard-coded Transformer. |
Revisiting Simple Neural Probabilistic Language Models (2021.naacl-main)
Copied to clipboard
| Challenge: | Recent advances in language modeling have been driven not only by advances in neural architectures, but also through hardware and optimization improvements. |
| Approach: | They revisit the neural probabilistic language model (NPLM) of Bengio et al. (2003) which simply concatenates word embeddings within a fixed window and passes the result through a feed-forward network to predict the next word. |
| Outcome: | The proposed model performs better on word-level language model benchmarks than a baseline Transformer with short input contexts but struggles to handle long-term dependencies. |
The Feasibility of Embedding Based Automatic Evaluation for Single Document Summarization (D19-1)
Copied to clipboard
| Challenge: | Existing evaluation methods for summarization systems measure semantic overlap between a system summary and a human reference on word-string level. |
| Approach: | They propose to use distributed representations to evaluate system summary and human reference on word-string level. |
| Outcome: | The proposed representations outperform ROUGE on recent corpora but are less good on test data used in previous studies. |
Energy-Based Reranking: Improving Neural Machine Translation Using Energy-Based Models (2021.acl-long)
Copied to clipboard
Sumanta Bhattacharyya, Amirmohammad Rooshenas, Subhajit Naskar, Simeng Sun, Mohit Iyyer, Andrew McCallum
| Challenge: | Autoregressive neural machine translation (NMT) uses a tractable likelihood computation and efficient sampling. |
| Approach: | They propose to use an energy-based model to mimic the behavior of the task measure and use it to train an energy based re-ranking algorithm. |
| Outcome: | The proposed model improves on the samples drawn from the NMT with a higher BLEU score than the experimental model and the energy-based re-ranking algorithm. |
Suri: Multi-constraint Instruction Following in Long-form Text Generation (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing studies on instruction following focus on simple instructions and short responses . however, there are challenges associated with collecting preference judgments on long-form texts . |
| Approach: | They propose an instruction-following alignment method that uses dispreferred instructions to obtain negative feedback from dispvoted instructions. |
| Outcome: | The proposed model generates significantly longer texts than base models without significant quality degradation. |
How Does In-Context Learning Help Prompt Tuning? (2024.findings-eacl)
Copied to clipboard
| Challenge: | a growing number of parameter-efficient adaptation methods are needed to fine-tune large language models. |
| Approach: | They propose a method that combines prompt tuning and in-context learning to improve prompt tuning by concatenating a natural language demonstration with learned prompt embeddings. |
| Outcome: | The proposed method outperforms prompt tuning and prompt tuning on five language generation tasks. |
Efficiently Upgrading Multilingual Machine Translation Models to Support More Languages (2023.eacl-main)
Copied to clipboard
| Challenge: | Existing multilingual machine translation models need to be upgraded as data becomes available in more languages. |
| Approach: | They propose three techniques that speed up the effective learning of new languages and alleviate catastrophic forgetting . |
| Outcome: | The proposed techniques exceed the performance of a same-sized baseline model with 30% computation and recover the performance a larger model trained from scratch with over 50% reduction in computation. |