Search Results for author:
Found 106 papers, 35 papers with code
A Collaborative Multi-agent Reinforcement Learning Framework for Dialog Action Decomposition
Most reinforcement learning methods for dialog policy learning train a centralized agent that selects a predefined joint action concatenating domain name, intent type, and slot name.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
MiniMax-Remover: Taming Bad Noise Helps Video Object Removal
Motivated by the observation that text condition is not best suited for this task, we simplify the pretrained video generation model by removing textual input and cross-attention layers, resulting in a more lightweight and efficient model architecture in the first stage.
Bridging the Long-Term Gap: A Memory-Active Policy for Multi-Session Task-Oriented Dialogue
Based on this new dataset, we propose a Memory-Active Policy (MAP) that improves multi-session dialogue efficiency through a two-stage approach.
Self-Reasoning Language Models: Unfold Hidden Reasoning Chains with Few Reasoning Catalyst
Inference-time scaling has attracted much attention which significantly enhance the performance of Large Language Models (LLMs) in complex reasoning tasks by increasing the length of Chain-of-Thought.
Rethinking Stateful Tool Use in Multi-Turn Dialogues: Benchmarks and Challenges
Existing benchmarks that assess Language Models (LMs) as Language Agents (LAs) for tool use primarily focus on stateless, single-turn interactions or partial evaluations, such as tool selection in a single turn, overlooking the inherent stateful nature of interactions in multi-turn applications.
Rethinking Memory in AI: Taxonomy, Operations, Topics, and Future Directions
By reframing memory systems through the lens of atomic operations and representation types, this survey provides a structured and dynamic perspective on research, benchmark datasets, and tools related to memory in AI, clarifying the functional interplay in LLMs based agents while outlining promising directions for future research\footnote{The paper list, datasets, methods and tools are available at \href{https://github. com/Elvin-Yiming-Du/Survey_Memory_in_AI}{https://github. com/Elvin-Yiming-Du/Survey\_Memory\_in\_AI}.
OTC: Optimal Tool Calls via Reinforcement Learning
Tool-integrated reasoning (TIR) augments large language models (LLMs) with the ability to invoke external tools, such as search engines and code interpreters, to solve tasks beyond the capabilities of language-only reasoning.
WHERE and WHICH: Iterative Debate for Biomedical Synthetic Data Augmentation
In Biomedical Natural Language Processing (BioNLP) tasks, such as Relation Extraction, Named Entity Recognition, and Text Classification, the scarcity of high-quality data remains a significant challenge.
Harnessing the Reasoning Economy: A Survey of Efficient Reasoning for Large Language Models
Recent advancements in Large Language Models (LLMs) have significantly enhanced their ability to perform complex reasoning tasks, transitioning from fast and intuitive thinking (System 1) to slow and deep reasoning (System 2).
FReM: A Flexible Reasoning Mechanism for Balancing Quick and Slow Thinking in Long-Context Question Answering
Long-context question-answering (LCQA) systems have greatly benefited from the powerful reasoning capabilities of large language models (LLMs), which can be categorized into slow and quick reasoning modes.
EventWeave: A Dynamic Framework for Capturing Core and Supporting Events in Dialogue Systems
Existing large language models (LLMs) have shown remarkable progress in dialogue systems.
DAST: Difficulty-Aware Self-Training on Large Language Models
Present Large Language Models (LLM) self-training methods always under-sample on challenging queries, leading to inadequate learning on difficult problems which limits LLMs' ability.
PEARL: Towards Permutation-Resilient LLMs
The in-context learning (ICL) capability of large language models (LLMs) enables them to perform challenging tasks using provided demonstrations.
Señorita-2M: A High-Quality Instruction-based Dataset for General Video Editing by Video Specialists
On the other hand, end-to-end methods, which rely on edited video pairs for training, offer faster inference speeds but often produce poor editing results due to a lack of high-quality training video pairs.
Understanding and Mitigating the Bias Inheritance in LLM-based Data Augmentation on Downstream Tasks
We hope this work can provide valuable insights to the research of LLM data augmentation.
UAlign: Leveraging Uncertainty Estimations for Factuality Alignment on Large Language Models
Despite demonstrating impressive capabilities, Large Language Models (LLMs) still often struggle to accurately express the factual knowledge they possess, especially in cases where the LLMs' knowledge boundaries are ambiguous.
ToolFlow: Boosting LLM Tool-Calling Through Natural and Coherent Dialogue Synthesis
Data quality assessments demonstrate improvements in the naturalness and coherence of our synthesized dialogues.
Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering
In this work, we propose \textsc{SpARE}, a \emph{training-free} representation engineering method that uses pre-trained sparse auto-encoders (SAEs) to control the knowledge selection behaviour of LLMs.
Analysing the Residual Stream of Language Models Under Knowledge Conflicts
Through probing tasks, we find that LLMs can internally register the signal of knowledge conflict in the residual stream, which can be accurately detected by probing the intermediate model activations.
MlingConf: A Comprehensive Study of Multilingual Confidence Estimation on Large Language Models
This paper addresses this gap by introducing a comprehensive investigation of Multilingual Confidence estimation (MlingConf) on LLMs, focusing on both language-agnostic (LA) and language-specific (LS) tasks to explore the performance and language dominance effects of multilingual confidence estimations on different tasks.
AppBench: Planning of Multiple APIs from Various APPs for Complex User Instruction
In this paper, we introduce \texttt{AppBench}, the first benchmark to evaluate LLMs' ability to plan and execute multiple APIs from various sources in order to complete the user's task.
VLEU: a Method for Automatic Evaluation for Generalizability of Text-to-Image Models
Progress in Text-to-Image (T2I) models has significantly improved the generation of images from textual descriptions.
Chain-of-Probe: Examing the Necessity and Accuracy of CoT Step-by-Step
To address these questions, we propose a method, namely Chain-of-Probe (CoP), to probe changes in the mind during the model's reasoning.
SeRTS: Self-Rewarding Tree Search for Biomedical Retrieval-Augmented Generation
By combining the reasoning capabilities of LLMs with the effectiveness of tree search, SeRTS boosts the zero-shot performance of retrieving high-quality and informative results for RAG.
OSPC: Detecting Harmful Memes with Large Language Model as a Catalyst
Utilizing the BLIP model for image captioning, PP-OCR and TrOCR for text recognition across multiple languages, and the Qwen LLM for nuanced language understanding, our system is capable of identifying harmful content in memes created in English, Chinese, Malay, and Tamil.
Visually Guided Generative Text-Layout Pre-training for Document Intelligence
Prior study shows that pre-training techniques can boost the performance of visual document understanding (VDU), which typically requires models to gain abilities to perceive and reason both document texts and layouts (e. g., locations of texts and table-cells).
CoCoCo: Improving Text-Guided Video Inpainting for Better Consistency, Controllability and Compatibility
To this end, this paper proposes a novel text-guided video inpainting model that achieves better consistency, controllability and compatibility.
Role Prompting Guided Domain Adaptation with General Capability Preserve for Large Language Models
2) Role Prompting assigns a central prompt to the general domain and a unique role prompt to each specific domain to minimize inter-domain confusion during training.
UniRetriever: Multi-task Candidates Selection for Various Context-Adaptive Conversational Retrieval
Conversational retrieval refers to an information retrieval system that operates in an iterative and interactive manner, requiring the retrieval of various external resources, such as persona, knowledge, and even response, to effectively engage with the user and successfully complete the dialogue.
PerLTQA: A Personal Long-Term Memory Dataset for Memory Classification, Retrieval, and Synthesis in Question Answering
This dataset is collected to investigate the use of personalized memories, focusing on social interactions and events in the QA task.
Mitigating Biases of Large Language Models in Stance Detection with Counterfactual Augmented Calibration
Therefore, in this paper, we propose a Counterfactual Augmented Calibration Network (FACTUAL), which a novel calibration network is devised to calibrate potential bias in the stance prediction of LLMs.
COPR: Continual Human Preference Learning via Optimal Policy Regularization
Reinforcement Learning from Human Feedback (RLHF) is commonly utilized to improve the alignment of Large Language Models (LLMs) with human preferences.
Multi-modal Stance Detection: New Datasets and Model
Stance detection is a challenging task that aims to identify public opinion from social media platforms with respect to specific targets.
A Comprehensive Study of Multilingual Confidence Estimation on Large Language Models
This paper addresses this gap by introducing a comprehensive investigation of Multilingual Confidence estimation (MlingConf) on LLMs, focusing on both language-agnostic (LA) and language-specific (LS) tasks to explore the performance and language dominance effects of multilingual confidence estimations on different tasks.
Self-DC: When to Reason and When to Act? Self Divide-and-Conquer for Compositional Unknown Questions
Previous research has typically concentrated on leveraging the internal knowledge of Large Language Models (LLMs) to answer known questions (i. e., \textit{internal reasoning such as generate-then-read}).
Selective Forgetting: Advancing Machine Unlearning Techniques and Evaluation in Language Models
In summary, this paper contributes a novel selective unlearning method (SeUL), introduces specialized evaluation metrics (S-EL and S-MA) for assessing sensitive information forgetting, and proposes automatic online and offline sensitive span annotation methods to support the overall unlearning framework and evaluation process.
IndiVec: An Exploration of Leveraging Large Language Models for Media Bias Detection with Fine-Grained Bias Indicators
IndiVec begins by constructing a fine-grained media bias database, leveraging the robust instruction-following capabilities of large language models and vector database techniques.
MT-Eval: A Multi-Turn Capabilities Evaluation Benchmark for Large Language Models
Large language models (LLMs) are increasingly relied upon for complex multi-turn conversations across diverse real-world applications.
UniMS-RAG: A Unified Multi-source Retrieval-Augmented Generation for Personalized Dialogue Systems
To better plan and incorporate the use of multiple sources in generating personalized response, we firstly decompose it into three sub-tasks: Knowledge Source Selection, Knowledge Retrieval, and Response Generation.
A Survey of the Evolution of Language Model-Based Dialogue Systems
This survey delves into the historical trajectory of dialogue systems, elucidating their intricate relationship with advancements in language models by categorizing this evolution into four distinct stages, each marked by pivotal LM breakthroughs: 1) Early_Stage: characterized by statistical LMs, resulting in rule-based or machine-learning-driven dialogue_systems; 2) Independent development of TOD and ODD based on neural_language_models (NLM; e. g., LSTM and GRU), since NLMs lack intrinsic knowledge in their parameters; 3) fusion between different types of dialogue systems with the advert of pre-trained_language_models (PLMs), starting from the fusion between four_sub-tasks_within_TOD, and then TOD_with_ODD; and 4) current LLM-based_dialogue_system, wherein LLMs can be used to conduct TOD and ODD seamlessly.
WatME: Towards Lossless Watermarking Through Lexical Redundancy
Text watermarking has emerged as a pivotal technique for identifying machine-generated text.
M4LE: A Multi-Ability Multi-Range Multi-Task Multi-Domain Long-Context Evaluation Benchmark for Large Language Models
In this paper, we propose M4LE, a Multi-ability, Multi-range, Multi-task, Multi-domain benchmark for Long-context Evaluation.
Self-Guard: Empower the LLM to Safeguard Itself
Currently, there are two main approaches to address jailbreak attacks: safety training and safeguards.
Large Language Models as Source Planner for Personalized Knowledge-grounded Dialogue
Open-domain dialogue system usually requires different sources of knowledge to generate more informative and evidential responses.
Improving Factual Consistency for Knowledge-Grounded Dialogue Systems via Knowledge Enhancement and Alignment
Inspired by previous work which identified that feed-forward networks (FFNs) within Transformers are responsible for factual knowledge expressions, we investigate two methods to efficiently improve the factual expression capability {of FFNs} by knowledge enhancement and alignment respectively.
Beyond Factuality: A Comprehensive Evaluation of Large Language Models as Knowledge Generators
Large language models (LLMs) outperform information retrieval techniques for downstream knowledge-intensive tasks when being prompted to generate world knowledge.
TPE: Towards Better Compositional Reasoning over Conceptual Tools with Multi-persona Collaboration
Large language models (LLMs) have demonstrated exceptional performance in planning the use of various functional tools, such as calculators and retrievers, particularly in question-answering tasks.
Dialog Action-Aware Transformer for Dialog Policy Learning
Recent works usually address Dialog policy learning DPL by training a reinforcement learning (RL) agent to determine the best dialog action.
Delta-LoRA: Fine-Tuning High-Rank Parameters with the Delta of Low-Rank Matrices
In this paper, we present Delta-LoRA, which is a novel parameter-efficient approach to fine-tune large language models (LLMs).
JoTR: A Joint Transformer and Reinforcement Learning Framework for Dialog Policy Learning
In addition, JoTR employs reinforcement learning with a reward-shaping mechanism to efficiently finetune the word-level dialogue policy, which allows the model to learn from its interactions, improving its performance over time.
CoAD: Automatic Diagnosis through Symptom and Disease Collaborative Generation
Automatic diagnosis (AD), a critical application of AI in healthcare, employs machine learning techniques to assist doctors in gathering patient symptom information for precise disease diagnosis.
UniTRec: A Unified Text-to-Text Transformer and Joint Contrastive Learning Framework for Text-based Recommendation
Moreover, conditioned on user history encoded by Transformer encoders, our framework leverages Transformer decoders to estimate the language perplexity of candidate text items, which can serve as a straightforward yet significant contrastive signal for user-item text matching.
Enhancing Large Language Models Against Inductive Instructions with Dual-critique Prompting
Numerous works are proposed to align large language models (LLMs) with human intents to better fulfill instructions, ensuring they are trustful and helpful.
Towards Robust Personalized Dialogue Generation via Order-Insensitive Representation Regularization
Generating persona consistent dialogue response is important for developing an intelligent conversational agent.
Cue-CoT: Chain-of-thought Prompting for Responding to In-depth Dialogue Questions with LLMs
Large Language Models (LLMs), such as \texttt{ChatGPT}, greatly empower dialogue systems with strong language understanding and generation capabilities.
KGA: A General Machine Unlearning Framework Based on Knowledge Gap Alignment
Recent legislation of the "right to be forgotten" has led to the interest in machine unlearning, where the learned models are endowed with the function to forget information about specific training instances as if they have never existed in the training set.
Strategize Before Teaching: A Conversational Tutoring System with Pedagogy Self-Distillation
Conversational tutoring systems (CTSs) aim to help students master educational material with natural language interaction in the form of a dialog.
DIGAT: Modeling News Recommendation with Dual-Graph Interaction
Second, existing graph-based NR methods are promising but lack effective news-user feature interaction, rendering the graph-based recommendation suboptimal.
Improving Conversational Recommender System via Contextual and Time-Aware Modeling with Less Domain-Specific Knowledge
In addition to conducting experiments on a popular dataset (ReDial), we also include a multi-domain dataset (OpenDialKG) to show the effectiveness of our model.
A Survey on Recent Advances and Challenges in Reinforcement Learning Methods for Task-Oriented Dialogue Policy Learning
In this paper, we survey recent advances and challenges in dialogue policy from the prescriptive of RL.
Integrating Pretrained Language Model for Dialogue Policy Learning
Reinforcement Learning (RL) has been witnessed its potential for training a dialogue policy agent towards maximizing the accumulated rewards given from users.
RecInDial: A Unified Framework for Conversational Recommendation with Pretrained Language Models
Furthermore, we propose to evaluate the CRS models in an end-to-end manner, which can reflect the overall performance of the entire system rather than the performance of individual modules, compared to the separate evaluations of the two modules used in previous work.
Inconsistent Few-Shot Relation Classification via Cross-Attentional Prototype Networks with Contrastive Learning
However, previous works rarely investigate the effects of a different number of classes (i. e., $N$-way) and number of labeled data per class (i. e., $K$-shot) during training vs. testing.
TopicRefine: Joint Topic Prediction and Dialogue Response Generation for Multi-turn End-to-End Dialogue System
A multi-turn dialogue always follows a specific topic thread, and topic shift at the discourse level occurs naturally as the conversation progresses, necessitating the model's ability to capture different topics and generate topic-aware responses.
Prior Omission of Dissimilar Source Domain(s) for Cost-Effective Few-Shot Learning
To tackle this problem, we propose an effective similarity-based method to select data from the source domains.
Re-entry Prediction for Online Conversations via Self-Supervised Learning
In recent years, world business in online discussions and opinion sharing on social media is booming.
Neural News Recommendation with Collaborative News Encoding and Structural User Encoding
In this work, we propose a news recommendation framework consisting of collaborative news encoding (CNE) and structural user encoding (SUE) to enhance news and user representation learning.
MCML: A Novel Memory-based Contrastive Meta-Learning Method for Few Shot Slot Tagging
Meta-learning is widely used for few-shot slot tagging in task of few-shot learning.
Continuity of Topic, Interaction, and Query: Learning to Quote in Online Conversations
Quotations are crucial for successful explanations and persuasions in interpersonal communications.
Quotation Recommendation and Interpretation Based on Transformation from Queries to Quotations
To help individuals express themselves better, quotation recommendation is receiving growing attention.
KddRES: A Multi-level Knowledge-driven Dialogue Dataset for Restaurant Towards Customized Dialogue System
In this paper, we publish a first Cantonese knowledge-driven Dialogue Dataset for REStaurant (KddRES) in Hong Kong, which grounds the information in multi-turn conversations to one specific restaurant.
Learning Efficient Dialogue Policy from Demonstrations through Shaping
Training a task-oriented dialogue agent with reinforcement learning is prohibitively expensive since it requires a large volume of interactions with users.
Dynamic Online Conversation Recommendation
Trending topics in social media content evolve over time, and it is therefore crucial to understand social media users and their interpersonal communications in a dynamic manner.
CUHK at SemEval-2020 Task 4: CommonSense Explanation, Reasoning and Prediction with Multi-task Learning
This paper describes our system submitted to task 4 of SemEval 2020: Commonsense Validation and Explanation (ComVE) which consists of three sub-tasks.
Fast and Scalable Dialogue State Tracking with Explicit Modular Decomposition
We present a fast and scalable architecture called Explicit Modular Decomposition (EMD), in which we incorporate both classification-based and extraction-based methods and design four modules (for classification and sequence labelling) to jointly extract dialogue states.
Neural Conversation Recommendation with Online Interaction Modeling
The prevalent use of social media leads to a vast amount of online conversations being produced on a daily basis.
Coupling Global and Local Context for Unsupervised Aspect Extraction
Aspect words, indicating opinion targets, are essential in expressing and understanding human opinions.
Sentence-Level Evidence Embedding for Claim Verification with Hierarchical Attention Networks
Claim verification is generally a task of verifying the veracity of a given claim, which is critical to many downstream applications.
Joint Effects of Context and User History for Predicting Online Conversation Re-entries
We hypothesize that both the context of the ongoing conversations and the users' previous chatting history will affect their continued interests in future engagement.
A Joint Model of Conversational Discourse Latent Topics on Microblogs
To address this issue, we organize microblog messages as conversation trees based on their reposting and replying relations, and propose an unsupervised model that jointly learns word distributions to represent: (1) different roles of conversational discourse, and (2) various latent topics in reflecting content information.
A Joint Model of Conversational Discourse and Latent Topics on Microblogs
To address this issue, we organize microblog messages as conversation trees based on their reposting and replying relations, and propose an unsupervised model that jointly learns word distributions to represent: 1) different roles of conversational discourse, 2) various latent topics in reflecting content information.
Task-oriented Dialogue System for Automatic Diagnosis
In this paper, we make a move to build a dialogue system for automatic diagnosis.
Rumor Detection on Twitter with Tree-structured Recursive Neural Networks
Automatic rumor detection is technically very challenging.
Microblog Conversation Recommendation via Joint Modeling of Topics and Discourse
We propose a statistical model that jointly captures: (1) topics for representing user interests and conversation content, and (2) discourse modes for describing user replying behavior and conversation dynamics.
Deep Dyna-Q: Integrating Planning for Task-Completion Dialogue Policy Learning
During dialogue policy learning, the world model is constantly updated with real user experience to approach real user behavior, and in turn, the dialogue agent is optimized using both real experience and simulated experience.
IJCNLP-2017 Task 2: Dimensional Sentiment Analysis for Chinese Phrases
This paper presents the IJCNLP 2017 shared task on Dimensional Sentiment Analysis for Chinese Phrases (DSAP) which seeks to identify a real-value sentiment score of Chinese single words and multi-word phrases in the both valence and arousal dimensions.
NLPTEA 2017 Shared Task -- Chinese Spelling Check
This paper provides an overview along with our findings of the Chinese Spelling Check shared task at NLPTEA 2017.
Adversarial Advantage Actor-Critic Model for Task-Completion Dialogue Policy Learning
This paper presents a new method --- adversarial advantage actor-critic (Adversarial A2C), which significantly improves the efficiency of dialogue policy learning in task-completion dialogue systems.
Detect Rumors in Microblog Posts Using Propagation Structure via Kernel Learning
How fake news goes viral via social media?
Composite Task-Completion Dialogue Policy Learning via Hierarchical Deep Reinforcement Learning
Building a dialogue agent to fulfill complex tasks, such as travel planning, is challenging because the agent has to learn to collectively complete multiple subtasks.
May I take your order? A Neural Model for Extracting Structured Information from Conversations
This is motivated by an actual system under development to assist in the order taking process.
ACE: Automatic Colloquialism, Typographical and Orthographic Errors Detection for Chinese Language
We present a system called ACE for Automatic Colloquialism and Errors detection for written Chinese.
An Attentional Neural Conversation Model with Improved Specificity
Experimental results indicate that the model outperforms previously proposed neural conversation architectures, and that using specificity in the objective function significantly improves performances for both generation and retrieval.
Towards Neural Network-based Reasoning
For example, it improves the accuracy on Path Finding(10K) from 33. 4% [6] to over 98%.
The CUHK Discourse TreeBank for Chinese: Annotating Explicit Discourse Connectives for the Chinese TreeBank
The lack of open discourse corpus for Chinese brings limitations for many natural language processing tasks.
Quantising Opinions for Political Tweets Analysis
There have been increasing interests in recent years in analyzing tweet messages relevant to political events so as to understand public opinions towards certain political issues.
