Related papers: Reproduction Beyond Benchmarks: ConstBERT and ColB…

The accelerating pace of research on autoregressive generative models has produced thousands of papers, making manual literature surveys and reproduction studies increasingly impractical. We present a fully open-source, reproducible…

In spite of great advancements of machine reading comprehension (RC), existing RC models are still vulnerable and not robust to different types of adversarial examples. Neural models over-confidently predict wrong answers to semantic…

This study evaluates large language models (LLMs) in generating code from algorithm descriptions in recent NLP papers. The task requires two key competencies: (1) algorithm comprehension: synthesizing information from papers and academic…

Autonomous research systems capable of generating complete scientific manuscripts have advanced rapidly, yet robust and realistic evaluation frameworks have failed to keep pace. To bridge this gap, we introduce MLReplicate, an end-to-end…

The XTR (conteXtual Token Retrieval) algorithm is a modification to ColBERT retrieval that avoids the costly step of fully gathering and reranking the candidates' embeddings by imputing their missing similarity scores from the initial token…

Newly-introduced deep learning architectures, namely BERT, XLNet, RoBERTa and ALBERT, have been proved to be robust on several NLP tasks. However, the datasets trained on these architectures are fixed in terms of size and generalizability.…

Retrieval-augmented language models (RALMs) hold promise to produce language understanding systems that are are factual, efficient, and up-to-date. An important desideratum of RALMs, is that retrieved information helps model performance…

When fine-tuning BERT models for specific tasks, it is common to select part of the final layer's output and input it into a newly created fully connected layer. However, it remains unclear which part of the final layer should be selected…

Large-scale supervised pretraining is rapidly reshaping 3D medical image segmentation. However, existing efforts focus primarily on increasing dataset size and overlook the question of whether the backbone network is an effective…

The miscalibration of Large Reasoning Models (LRMs) undermines their reliability in high-stakes domains, necessitating methods to accurately estimate the confidence of their long-form, multi-step outputs. To address this gap, we introduce…

Every system that maintains a large language model conversation beyond a single session faces two inescapable constraints: the context window is finite, and information quality degrades with accumulated volume. We formalize these…

Narrative understanding requires multidimensional semantic structures. This study investigates whether BERT embeddings encode dimensions of fictional narrative semantics -- time, space, causality, and character. Using an LLM to accelerate…

Long-running autonomous AI agents suffer from a well-documented memory coherence problem: tool-execution success rates degrade 14 percentage points over 72-hour operation windows due to four compounding failure modes in existing flat-file…

We study the problem of recovering an incomplete $m\times n$ matrix of rank $r$ with columns arriving online over time. This is known as the problem of life-long matrix completion, and is widely applied to recommendation system, computer…

Pre-trained large-scale language models such as BERT have gained a lot of attention thanks to their outstanding performance on a wide range of natural language tasks. However, due to their large number of parameters, they are…

The current state-of-the-art task-oriented semantic parsing models use BERT or RoBERTa as pretrained encoders; these models have huge memory footprints. This poses a challenge to their deployment for voice assistants such as Amazon Alexa…

Reinforcement Learning with Verifiable Rewards~(RLVR) has become a prominent paradigm to enhance the capabilities (i.e.\ long-context) of Large Language Models~(LLMs). However, it often relies on gold-standard answers or explicit evaluation…

Fully comprehending scientific papers by machines reflects a high level of Artificial General Intelligence, requiring the ability to reason across fragmented and heterogeneous sources of information, presenting a complex and practically…

Late interaction neural IR models like ColBERT offer a competitive effectiveness-efficiency trade-off across many benchmarks. However, they require a huge memory space to store the contextual representation for all the document tokens. Some…

In this paper, we investigate the impact of different standard environmental sound representations (spectrograms) on the recognition performance and adversarial attack robustness of a victim residual convolutional neural network. Averaged…