Related papers: PuzLM: Solving Jigsaw Puzzles with Sequence-to-Seq…
Reasoning over procedural sequences, where the order of steps directly impacts outcomes, is a critical capability for large language models (LLMs). In this work, we study the task of reconstructing globally ordered sequences from shuffled…
Post-training quantization (PTQ) of large language models (LLMs) holds the promise in reducing the prohibitive computational cost at inference time. Quantization of all weight, activation and key-value (KV) cache tensors to 4-bit without…
Large Language Models (LLMs) have achieved impressive results across numerous domains, yet they experience notable deficiencies in legal question-answering tasks. LLMs often generate generalized responses that lack the logical specificity…
Large Language Models (LLMs) are known to produce very high-quality tests and responses to our queries. But how much can we trust this generated text? In this paper, we study the problem of uncertainty quantification in LLMs. We propose a…
With the rise of multimodal learning, image retrieval plays a crucial role in connecting visual information with natural language queries. Existing image retrievers struggle with processing long texts and handling unclear user expressions.…
Large Vision-Language Models (LVLMs) have achieved remarkable proficiency in explicit visual recognition, effectively describing what is directly visible in an image. However, a critical cognitive gap emerges when the visual input serves…
We present the Linear Complexity Sequence Model (LCSM), a comprehensive solution that unites various sequence modeling techniques with linear complexity, including linear attention, state space model, long convolution, and linear RNN,…
Generating accurate circuit schematics from high-level natural language descriptions remains a persistent challenge in electronic design automation (EDA), as large language models (LLMs) frequently hallucinate components, violate strict…
In this work, we explore a genre of puzzles ("image riddles") which involves a set of images and a question. Answering these puzzles require both capabilities involving visual detection (including object, activity recognition) and,…
Solving arithmetic word problems is a cornerstone task in assessing language understanding and reasoning capabilities in NLP systems. Recent works use automatic extraction and ranking of candidate solution equations providing the answer to…
Software documentation frequently becomes outdated or fails to exist entirely, yet developers need focused views of their codebase to understand complex systems. While automated reverse engineering tools can generate UML diagrams from code,…
Natural language generation (NLG) is a critical component in spoken dialogue system, which can be divided into two phases: (1) sentence planning: deciding the overall sentence structure, (2) surface realization: determining specific word…
We introduce a novel sequential modeling approach which enables learning a Large Vision Model (LVM) without making use of any linguistic data. To do this, we define a common format, "visual sentences", in which we can represent raw images…
While large language models (LLMs) have made notable advancements in natural language processing, they continue to struggle with processing extensive text. Memory mechanism offers a flexible solution for managing long contexts, utilizing…
We provide here a dataset for tasks related to natural language understanding and natural language inference. The dataset contains logical puzzles in natural language from three domains: comparing puzzles, knighs and knaves, and zebra…
We address an important problem in sequence-to-sequence (Seq2Seq) learning referred to as copying, in which certain segments in the input sequence are selectively replicated in the output sequence. A similar phenomenon is observable in…
This paper provides a comprehensive analysis of the first shared task on End-to-End Natural Language Generation (NLG) and identifies avenues for future research based on the results. This shared task aimed to assess whether recent…
This work proposes a novel approach based on sequence-to-sequence (seq2seq) models for context-aware conversational systems. Exist- ing seq2seq models have been shown to be good for generating natural responses in a data-driven…
This paper demonstrates that language models are strong structure-based protein designers. We present LM-Design, a generic approach to reprogramming sequence-based protein language models (pLMs), that have learned massive sequential…
Causal language modeling (LM) uses word history to predict the next word. BERT, on the other hand, makes use of bi-directional word information in a sentence to predict words at masked positions. While BERT is effective in sequence…