Search Results for author:
Found 21 papers, 14 papers with code
BriLLM: Brain-inspired Large Language Model
In the language model scenario, the token is defined as a node in the graph.
Towards Enhanced Immersion and Agency for LLM-based Interactive Drama
LLM-based Interactive Drama is a novel AI-based dialogue scenario, where the user (i. e. the player) plays the role of a character in the story, has conversations with characters played by LLM agents, and experiences an unfolding story.
Instruction-Driven Game Engine: A Poker Case Study
The IDGE allows users to create games simply by natural language instructions, which significantly lowers the barrier for game development.
A Coin Has Two Sides: A Novel Detector-Corrector Framework for Chinese Spelling Correction
Our detector is designed to yield two error detection results, each characterized by high precision and recall.
Self-Directed Turing Test for Large Language Models
This fails to reflect a natural conversational style and hinders the evaluation of Large Language Models (LLMs) in complex and prolonged dialogues.
Game Development as Human-LLM Interaction
Game development is a highly specialized task that relies on a complex game engine powered by complex programming languages, preventing many gaming enthusiasts from handling it.
Open Role-Playing with Delta-Engines
In this paper, we propose a new style of game-play to bridge self-expression and role-playing: \emph{open role-playing games (ORPGs)}, where players are allowed to craft and embody their unique characters in the game world.
From Role-Play to Drama-Interaction: An LLM Solution
Drama is a form of storytelling inspired by human creativity, proceeding with a predefined storyline, carrying emotions and thoughts.
Instruction-Driven Game Engines on Large Language Models
The Instruction-Driven Game Engine (IDGE) project aims to democratize game development by enabling a large language model (LLM) to follow free-form game rules and autonomously generate game-play processes.
Unveiling Vulnerability of Self-Attention
(2) We introduce \textit{S-Attend}, a novel smoothing technique that effectively makes SA robust via structural perturbations.
Episodic Return Decomposition by Difference of Implicitly Assigned Sub-Trajectory Reward
Real-world decision-making problems are usually accompanied by delayed rewards, which affects the sample efficiency of Reinforcement Learning, especially in the extremely delayed case where the only feedback is the episodic reward obtained at the end of an episode.
Empower Nested Boolean Logic via Self-Supervised Curriculum Learning
Beyond the great cognitive powers showcased by language models, it is crucial to scrutinize whether their reasoning capabilities stem from strong generalization or merely exposure to relevant data.
Chinese Spelling Correction as Rephrasing Language Model
However, we note a critical flaw in the process of tagging one character to another, that the correction is excessively conditioned on the error.
Rethinking Masked Language Modeling for Chinese Spelling Correction
In this paper, we study Chinese Spelling Correction (CSC) as a joint decision made by two separate models: a language model and an error model.
Attack Named Entity Recognition by Entity Boundary Interference
This is due to the fine-grained nature of NER, as even minor word changes in the sentence can result in the emergence or mutation of any entities, resulting in invalid adversarial examples.
Toward Adversarial Training on Contextualized Language Representation
Based on the observation, we propose simple yet effective \textit{Contextualized representation-Adversarial Training} (CreAT), in which the attack is explicitly optimized to deviate the contextualized representation of the encoder.
Forging Multiple Training Objectives for Pre-trained Language Models via Meta-Learning
Multiple pre-training objectives fill the vacancy of the understanding capability of single-objective language modeling, which serves the ultimate purpose of pre-trained language models (PrLMs), generalizing well on a mass of scenarios.
Semantic-Preserving Adversarial Code Comprehension
Based on the tremendous success of pre-trained language models (PrLMs) for source code comprehension tasks, current literature studies either ways to further improve the performance (generalization) of PrLMs, or their robustness against adversarial attacks.
Adversarial Self-Attention for Language Understanding
Deep neural models (e. g. Transformer) naturally learn spurious features, which create a ``shortcut'' between the labels and inputs, thus impairing the generalization and robustness.
Ranked #1 on
Machine Reading Comprehension
on DREAM
Machine Reading Comprehension
Named Entity Recognition (NER)
+4
Not All Attention Is All You Need
Beyond the success story of pre-trained language models (PrLMs) in recent natural language processing, they are susceptible to over-fitting due to unusual large model size.
Code Summarization with Structure-induced Transformer
Code summarization (CS) is becoming a promising area in recent language understanding, which aims to generate sensible human language automatically for programming language in the format of source code, serving in the most convenience of programmer developing.
