87 accepted papers
Reinforcement fine-tuning (RFT) often suffers from reward over-optimization, where a policy model hacks the reward signals to achieve high scores while producing low-quality outputs. Our theoretical analysis shows that the key lies in reward misspecification at the high-reward tail: the inability to…
Continual learning (CL) aims to enable models to incrementally learn from a sequence of tasks without forgetting previously acquired knowledge. While most prior work focuses on closed-world settings, where all test instances are assumed from the set of learned classes, real-world applications requir
*Model merging* offers an appealing route to multi-task learning by composing independently fine-tuned checkpoints without centralized data or retraining. However, this convenience can come with a hidden cost. Model merging may *amplify* performance disparities across subgroups, raising fairness con…
The scarcity of paired gene expression and pathology images datasets poses a major bottleneck for training large-scale pathology foundation models. Although gene-to-image generative models offer a promising solution, existing methods typically employ coarse-grained conditional control strategies, re
Large language models (LLMs) are substantial investments and increasingly deployed in high-stakes domains, making it critical to protect LLM-related assets and to trace their provenance.Identity technologies such as fingerprinting and watermarking address these needs by enabling ownership verificati
Competitive programming is increasingly being used to evaluate the algorithmic reasoning capabilities of large language models (LLMs). However, existing benchmarks primarily focus on full-information tasks where all problem inputs are provided upfront. This overlooks a critical dimension of algorith…
As AI systems progresses, we rely more on them to make decisions with us and for us. To ensure that such decisions are aligned with human values, it is imperative for us to understand not only what decisions they make but also how they come to those decisions. Reasoning language models, which provid…
Text-only training provides an attractive approach to address data scarcity challenges in zero-shot image captioning (ZIC), avoiding the expense of collecting paired image-text annotations. However, although these approaches perform well within training domains, they suffer from poor cross-domain ge
Rubrics provide a flexible way to train LLMs on open-ended long-form answers where verifiable rewards are not applicable and human preferences provide coarse signals. Prior work shows that reinforcement learning with rubric-based rewards leads to consistent gains in LLM post-training. Most existing …
Linear attention architectures based on the Delta rule, such as DeltaNet and RWKV-7, combine Transformers' training scalability with RNNs' inference efficiency and can provably solve regular language tasks. However, due to their fixed-size state, these models fundamentally struggle to capture the re…
Deep Research (DR) is an emerging agent application that leverages large language models (LLMs) to address open-ended queries. It requires the integration of several capabilities, including multi-step reasoning, cross-document synthesis, and the generation of evidence-backed, long-form answers. Eval…
Decentralized learning often involves a weighted global loss with heterogeneous node weights $\lambda$. We revisit two natural strategies for incorporating these weights: (i) embedding them into the local losses to retain a uniform weight (and thus a doubly stochastic matrix), and (ii) keeping the o…
Reinforcement Learning with Verifiable Rewards (RLVR) has proven effective for complex reasoning tasks with clear correctness signals such as math and coding. However, extending it to real-world reasoning tasks is challenging, as evaluation depends on nuanced, multi-criteria judgments rather than bi…
We present SWE-Bench Pro, a comprehensive benchmark designed to evaluate software engineering capabilities through complex, realistic programming challenges. This benchmark extends beyond traditional algorithmic problems to encompass the full spectrum of professional software development tasks. The …
Accelerating scientific discovery requires the identification of which experiments would yield the best outcomes before committing resources to costly physical validation. While existing benchmarks evaluate LLMs on scientific knowledge and reasoning, their ability to predict experimental outcomes---…
This paper studies the problem of class-incremental learning (CIL), a core setting within continual learning where a model learns a sequence of tasks, each containing a distinct set of classes. Traditional CIL methods, which do not leverage pre-trained models (PTMs), suffer from catastrophic forgett…
Large Language Models (LLMs) have achieved impressive results across numerous NLP tasks, and fine-tuning them for Machine Translation (MT) has improved their performance. However, vanilla fine-tuning often leads to catastrophic forgetting, compromising the broad general abilities of LLMs and introdu…
We introduce CLOB, a novel continual learning (CL) paradigm wherein a large language model (LLM) is regarded as a black box. Learning is done incrementally via only verbal prompting. CLOB does not fine-tune any part of the LLM or add any trainable parameters to it. It is particularly suitable for LL…
Continual learning (CL) learns a sequence of tasks incrementally. This paper studies the challenging CL setting of class-incremental learning (CIL). CIL has two key challenges: catastrophic forgetting (CF) and inter-task class separation (ICS). Despite numerous proposed methods, these issues remain…
Traditional unsupervised domain adaptation (UDA) struggles to extract rich semantics due to backbone limitations. Recent large-scale pre-trained visual-language models (VLMs) have shown strong zero-shot learning capabilities in UDA tasks. However, directly using VLMs results in a mixture of semantic
We explore the potential of \emph{AI-enhanced combinatorial optimization theory}, taking online bipartite matching (OBM) as a case study. In the theoretical study of OBM, the \emph{hardness} corresponds to a performance \emph{upper bound} of a specific online algorithm or any possible online algorit…
Length generalization (LG) is a challenging problem in learning to reason. It refers to the phenomenon that when trained on reasoning problems of smaller lengths/sizes, the model struggles with problems of larger sizes or lengths. Although it has been proven that reasoning can be learned if the inte…
Existing continual learning (CL) methods mainly rely on fine-tuning or adapting large language models (LLMs). They still suffer from catastrophic forgetting (CF). Little work has been done to exploit in-context learning (ICL) to leverage the extensive knowledge within LLMs for CL without updating an…
Model merging, such as model souping, is the practice of combining different models with the same architecture together without further training. In this work, we present a model merging methodology that addresses the difficulty of fine-tuning Large Language Models (LLMs) for target tasks in non-Eng…
To reduce the reliance on large-scale annotations, self-supervised RGB-T tracking approaches have garnered significant attention. However, the omission of the object region by erroneous pseudo-label or the introduction of background noise affects the efficiency of modality fusion, while pseudo-label
Network quantization, one of the most widely studied model compression methods, effectively quantizes a floating-point model to obtain a fixed-point one with negligible accuracy loss. Although great success was achieved in reducing the model size, it may exacerbate the unfairness in model accuracy…
LLM-based agents can greatly extend the abilities of LLMs and thus attract sharply increased studies. An ambitious vision – serving users by manipulating massive API-based tools – has been proposed and explored. However, we find a widely accepted evaluation mechanism for generic agents is still miss…
Class incremental learning (CIL) is a challenging setting of continual learning, which learns a series of tasks sequentially. Each task consists of a set of unique classes. The key feature of CIL is that no task identifier (or task-id) is provided at test time. Predicting the task-id for each test s…
Recently, Table Structure Recognition (TSR) task, aiming at identifying table structure into machine readable formats, has received increasing interest in the community. While impressive success, most single table component-based methods can not perform well on unregularized table cases distracted b…
Health coaching helps patients achieve personalized and lifestyle-related goals, effectively managing chronic conditions and alleviating mental health issues. It is particularly beneficial, however cost-prohibitive, for low-socioeconomic status populations due to its highly personalized and labor-in…
Several approaches have been proposed to pre-train an audio encoder to learn fundamental audio knowledge. These training frameworks range from supervised learning to self-supervised learning with a contrastive objective under multi-modal supervision. However, these approaches are constrained to a si…
In noisy label learning, instance selection based on small-loss criteria has been proven to be highly effective. However, in the case of noisy multi-label text classification (NMLTC), the presence of noise is not limited to the instance-level but extends to the (instance-label) pair-level.This gives…
Large Language Models (LLMs) have shown their impressive capabilities, while also raising concerns about the data contamination problems due to privacy issues and leakage of benchmark datasets in the pre-training phase. Therefore, it is vital to detect the contamination by checking whether an LLM ha…
Foundation Models (FMs) have demonstrated remarkable insights into the relational dynamics of the world, leading to the crucial question: *how do these models acquire an understanding of world hybrid relations?* Traditional statistical learning, particularly for prediction problems, may overlook the…
Class-incremental learning (CIL) aims to continually learn a sequence of tasks, with each task consisting of a set of unique classes. Graph CIL (GCIL) follows the same setting but needs to deal with graph tasks (e.g., node classification in a graph). The key characteristic of CIL lies in the absence…
Sentiment analysis (SA) has been a long-standing research area in natural language processing. With the recent advent of large language models (LLMs), there is great potential for their employment on SA problems. However, the extent to which current LLMs can be leveraged for different sentiment anal…
Large Language Model (LLM)-enhanced agents become increasingly prevalent in Human-AI communication, offering vast potential from entertainment to professional domains. However, current multi-modal dialogue systems overlook the acoustic information present in speech, which is crucial for understandin…
State-of-the-art natural language processing models have been shown to achieve remarkable performance in ‘closed-world’ settings where all the labels in the evaluation set are known at training time. However, in real-world settings, ‘novel’ instances that do not belong to any known class are often o…
Existing research has shown that a multilingual pre-trained language model fine-tuned with one (source) language also performs well on downstream tasks for non-source languages, even though no fine-tuning is done on these languages. However, there is a clear gap between the performance of the source…
Despite the great success of pre-trained language models, it is still a challenge to use these models for continual learning, especially for the class-incremental learning (CIL) setting due to catastrophic forgetting (CF). This paper reports our finding that if we formulate CIL as a continual label…
Language models (LMs) have been instrumental for the rapid advance of natural language processing. This paper studies continual pre-training of LMs, in particular, continual domain-adaptive pre-training (or continual DAP-training). Existing research has shown that further pre-training an LM using a…
Existing continual learning (CL) research regards catastrophic forgetting (CF) as almost the only challenge. This paper argues for another challenge in class-incremental learning (CIL), which we call cross-task class discrimination (CTCD), i.e., how to establish decision boundaries between the class…
As deep learning gains popularity in modelling dynamical systems, we expose an underappreciated misunderstanding relevant to modelling dynamics on networks. Strongly influenced by graph neural networks, latent vertex embeddings are naturally adopted in many neural dynamical network models. However,…
Recent studies find existing self-supervised speech encoders contain primarily acoustic rather than semantic information. As a result, pipelined supervised automatic speech recognition (ASR) to large language model (LLM) systems achieve state-of-the-art results on semantic spoken language tasks by u…
Multi-label text classification (MLTC) involves tagging a document with its most relevant subset of labels from a label set. In real applications, labels usually follow a long-tailed distribution, where most labels (called as tail-label) only contain a small number of documents and limit the perform…
This paper studies the challenging continual learning (CL) setting of Class Incremental Learning (CIL). CIL learns a sequence of tasks consisting of disjoint sets of concepts or classes. At any time, a single model is built that can be applied to predict/classify test instances of any classes learne…
In the field of information retrieval, Query Likelihood Models (QLMs) rank documents based on the probability of generating the query given the content of a document. Recently, advanced large language models (LLMs) have emerged as effective QLMs, showcasing promising ranking capabilities. This paper…
Existing research on task incremental learning in continual learning has primarily focused on preventing catastrophic forgetting (CF). Although several techniques have achieved learning with no CF, they attain it by letting each task monopolize a sub-network in a shared network, which seriously limi…
Continual learning (CL) has two main objectives: preventing catastrophic forgetting (CF) and encouraging knowledge transfer (KT). The existing literature mainly focused on overcoming CF. Some work has also been done on KT when the tasks are similar. To our knowledge, only one method has been propose…
Deploying deep learning models to new environments is very challenging. Domain adaptation (DA) is a promising paradigm to solve the problem by collecting and adapting to unlabeled data in new environments. Though research efforts have led to steady performance improvement over the past decade, DA al…
Continual learning (CL) learns a sequence of tasks incrementally. There are two popular CL settings, class incremental learning (CIL) and task incremental learning (TIL). A major challenge of CL is catastrophic forgetting (CF). While a number of techniques are already available to effectively overco…
Domain-adaptive pre-training (or DA-training for short), also known as post-training, aimsto train a pre-trained general-purpose language model (LM) using an unlabeled corpus of aparticular domain to adapt the LM so that end-tasks in the domain can give improved performances. However, existing DA-tr…
Catastrophic forgetting is a key obstacle to continual learning. One of the state-of-the-art approaches is orthogonal projection. The idea of this approach is to learn each task by updating the network parameters or weights only in the direction orthogonal to the subspace spanned by all previous tas…
Recent work on applying large language models (LMs) achieves impressive performance in many NLP applications. Adapting or posttraining an LM using an unlabeled domain corpus can produce even better performance for end-tasks in the domain. This paper proposes the problem of continually extending an L…
Entity alignment is to find identical entities in different knowledge graphs. Although embedding-based entity alignment has recently achieved remarkable progress, training data insufficiency remains a critical challenge. Conventional semi-supervised methods also suffer from the incorrect entity alig…
Entity Alignment (EA) aims to find equivalent entities between two Knowledge Graphs (KGs). While numerous neural EA models have been devised, they are mainly learned using labelled data only. In this work, we argue that different entities within one KG should have compatible counterparts in the othe…
Existing studies in dialogue system research mostly treat task-oriented dialogue and chit-chat as separate domains. Towards building a human-like assistant that can converse naturally and seamlessly with users, it is important to build a dialogue system that conducts both types of conversations effe…
Recently, table structure recognition has achieved impressive progress with the help of deep graph models. Most of them exploit single visual cues of tabular elements or simply combine visual cues with other modalities via early fusion to reason their graph relationships. However, neither early fusi…
This paper proposed a new online continual learning approach called OCM based on
Much of the existing work on text novelty detection has been studied at the topic level, i.e., identifying whether the topic of a document or a sentence is novel or not. Little work has been done at the fine-grained semantic level (or contextual level). For example, given that we know Elon Musk is t…
The transformer-based encoder-decoder framework has shown remarkable performance in image captioning. However, most transformer-based captioning methods ever overlook two kinds of elusive confounders: the visual confounder and the linguistic confounder, which generally lead to harmful bias, induce t…
Health coaching helps patients identify and accomplish lifestyle-related goals, effectively improving the control of chronic diseases and mitigating mental health conditions. However, health coaching is cost-prohibitive due to its highly personalized and labor-intensive nature. In this paper, we pro…
In an out-of-distribution (OOD) detection problem, samples of known classes (also called in-distribution classes) are used to train a special classifier. In testing, the classifier can (1) classify the test samples of known classes to their respective classes and also (2) detect samples that do not…
Continual learning (CL) learns a sequence of tasks incrementally with the goal of achieving two main objectives: overcoming catastrophic forgetting (CF) and encouraging knowledge transfer (KT) across tasks. However, most existing techniques focus only on overcoming CF and have no mechanism to encour…
Entity Alignment (EA) aims to match equivalent entities across different Knowledge Graphs (KGs) and is an essential step of KG fusion. Current mainstream methods – neural EA models – rely on training with seed alignment, i.e., a set of pre-aligned entity pairs which are very costly to annotate. In t…
This paper studies continual learning (CL) of a sequence of aspect sentiment classification (ASC) tasks. Although some CL techniques have been proposed for document sentiment classification, we are not aware of any CL work on ASC. A CL system that incrementally learns a sequence of ASC tasks should…
Existing dialogue corpora and models are typically designed under two disjoint motives: while task-oriented systems focus on achieving functional goals (e.g., booking hotels), open-domain chatbots aim at making socially engaging conversations. In this work, we propose to integrate both types of syst…
Continual learning (CL) of a sequence of tasks is often accompanied with the catastrophic forgetting(CF) problem. Existing research has achieved remarkable results in overcoming CF, especially for task continual learning. However, limited work has been done to achieve another important goal of CL,kn…
This paper studies continual learning (CL) of a sequence of aspect sentiment classification (ASC) tasks in a particular CL setting called domain incremental learning (DIL). Each task is from a different domain or product. The DIL setting is particularly suited to ASC because in testing the system ne…
Hierarchical Text Classification (HTC) is a challenging task that categorizes a textual description within a taxonomic hierarchy. Most of the existing methods focus on modeling the text. Recently, researchers attempt to model the class representations with some resources (e.g., external dictionaries…
Continual learning (CL) incrementally learns a sequence of tasks while solving the catastrophic forgetting (CF) problem. Existing methods mainly try to deal with CF directly. In this paper, we propose to avoid CF by considering the features of each class holistically rather than only the discrimin…
Continual learning in task-oriented dialogue systems allows the system to add new domains and functionalities overtime after deployment, without incurring the high cost of retraining the whole system each time. In this paper, we propose a first-ever continual learning benchmark for task-oriented dia…
Zero-shot cross-domain dialogue state tracking (DST) enables us to handle unseen domains without the expense of collecting in-domain data. In this paper, we propose a slot descriptions enhanced generative approach for zero-shot cross-domain DST. Specifically, our model first encodes a dialogue conte…
Existing conversational systems are mostly agent-centric, which assumes the user utterances will closely follow the system ontology. However, in real-world scenarios, it is highly desirable that users can speak freely and naturally. In this work, we attempt to build a user-centric dialogue system fo…
This paper studies learning from positive and unlabeled examples, known as PU learning. It proposes a novel PU learning method called Predictive Adversarial Networks (PAN) based on GAN (Generative Adversarial Networks). GAN learns a generator to generate data (e.g., images) to fool a discriminator w…
This paper proposes to study a fine-grained semantic novelty detection task, which can be illustrated with the following example. It is normal that a person walks a dog in the park, but if someone says “A man is walking a chicken in the park”, it is novel. Given a set of natural language description…
Zero-shot transfer learning for dialogue state tracking (DST) enables us to handle a variety of task-oriented dialogue domains without the expense of collecting in-domain data. In this work, we propose to transfer the cross-task knowledge from general question answering (QA) corpora for the zero-sho…
The classic deep learning paradigm learns a model from the training data of a single task and the learned model is also tested on the same task. This paper studies the problem of learning a sequence of tasks (sentiment classification tasks in our case). After each sentiment classification task is le…
Existing research on continual learning of a sequence of tasks focused on dealing with catastrophic forgetting, where the tasks are assumed to be dissimilar and have little shared knowledge. Some work has also been done to transfer previously learned knowledge to the new task when the tasks are simi…
Existing neural network based one-class learning methods mainly use various forms of auto-encoders or GAN style adversarial training to learn a latent representation of the given one class of data. This paper proposes an entirely different approach based on a novel regularization, called holistic re…
Sparsity is regarded as a desirable property of representations, especially in terms of explanation. However, its usage has been limited due to the gap with dense representations. Most research progresses in NLP in recent years are based on dense representations. Thus the desirable property of spars…
Understanding neural models is a major topic of interest in the deep learning community. In this paper, we propose to interpret a general neural model comparatively. Specifically, we study the sequence-to-sequence (Seq2Seq) model in the contexts of two mainstream NLP tasks–machine translation and di…
This paper analyzes the pre-trained hidden representations learned from reviews on BERT for tasks in aspect-based sentiment analysis (ABSA). Our work is motivated by the recent progress in BERT-based language models for ABSA. However, it is not clear how the general proxy task of (masked) language m…
We study an end-to-end approach for conversational recommendation that dynamically manages and reasons over users’ past (offline) preferences and current (online) requests through a structured and cumulative user memory knowledge graph. This formulation extends existing state tracking beyond the bou…
Learning multiple tasks sequentially is important for the development of AI and lifelong learning systems. However, standard neural network architectures suffer from catastrophic forgetting which makes it difficult for them to learn a sequence of tasks. Several continual learning methods have been p…
Asking questions is an important ability for a chatbot. This paper focuses on question generation. Although there are existing works on question generation based on a piece of descriptive text, it remains to be a very challenging problem. In the paper, we propose a new question generation problem, w…
In this work, we propose contextual language models that incorporate dialog level discourse information into language modeling. Previous works on contextual language model treat preceding utterances as a sequence of inputs, without considering dialog interactions. We design recurrent neural network…