67 accepted papers
LLM-based agents have seen promising advances, yet they are still limited in “hard-exploration” tasks requiring learning new knowledge through exploration. We present GLoW, a novel approach leveraging dual-scale world models, maintaining a trajectory frontier of high-value discoveries at the global…
Listwise reranking with large language models (LLMs) enhances top-ranked results in retrieval-based applications. Due to the limit in context size and high inference cost of long context, reranking is typically performed over a fixed size of small subsets, with the final ranking aggregated from thes…
Large Language Models (LLMs) have demonstrated near-human performance in summarization tasks based on traditional metrics such as ROUGE and BERTScore. However, these metrics do not adequately capture critical aspects of summarization quality, such as factual accuracy, particularly for long narrative
With the adoption of retrieval-augmented generation (RAG), large language models (LLMs) are expected to ground their generation to the retrieved contexts. Yet, this is hindered by position bias of LLMs, failing to evenly attend to all contexts. Previous work has addressed this by synthesizing contex…
Planning in modern LLM agents relies on the utilization of LLM as an internal world model, acquired during pretraining. However, existing agent designs fail to effectively assimilate new observations into dynamic updates of the world model. This reliance on the LLM’s static internal world model is p
Large language models (LLMs) have proven invaluable for code generation, particularly in interactive settings. However, existing code generation benchmarks fail to capture the diverse feedback encountered in multi-turn interactions, limiting our ability to evaluate LLMs in these contexts. To address…
Despite the advanced capabilities of large language models (LLMs), their temporal reasoning ability remains underdeveloped. Prior works have highlighted this limitation, particularly in maintaining temporal consistency when understanding event relations. For example, models often confuse mutually ex…
Large Language Models (LLMs) have shown remarkable performance in Open-Domain Question Answering (ODQA) by leveraging external documents through Retrieval-Augmented Generation (RAG). To reduce RAG overhead, from longer context, context compression is necessary. However, prior compression methods do…
Targeting long-form question-answering, chain-of-query (CoQ) has been studied, integrating chain-of-thought (CoT) with retrieval-augmented generation. CoQ answers the complex question step-by-step, through simpler subquestions (SQs) from which relevant knowledge is retrieved. By doing so, CoQ aims t…
Chain-of-Thought (CoT) prompting enables complex reasoning in large language models (LLMs), including applications in information retrieval (IR). However, it often leads to overthinking, where models produce excessively long and semantically redundant traces with little or no benefit. We identify tw
This paper aims to improve the performance of large language models by addressing the variable computational demands in inference steps, where some tokens require more computational resources than others. We present HARP, a simple modification to “off-the-shelf” Transformer forward pass. Drawing fro…
Entity alignment (EA) is crucial for integrating knowledge graphs (KGs) constructed from diverse sources. Conventional unsupervised EA approaches attempt to eliminate human intervention but often suffer from accuracy limitations. With the rise of large language models (LLMs), leveraging their capabi…
Retrieval-augmented generation (RAG) has emerged as a popular approach to steering the output of a large language model (LLM) by incorporating retrieved contexts as inputs. However, existing work observed the generator bias, such that improving the retrieval results may negatively affect the outcome…
Code generation with large language models has shown significant promise, especially when employing retrieval-augmented generation (RAG) with few-shot examples. However, selecting effective examples that enhance generation quality remains a challenging task, particularly when the target programming…
Fine-tuning large language models (LLMs) for code generation is challenging due to computational costs and the underrepresentation of some programming languages (PLs) in pre-training. We propose PLEX, a lottery-ticket based parameter-efficient fine-tuning (PEFT) method that adapts LLMs to either wel…
Large language models (LLMs) have become standard for natural language generation tasks, with instruction-tuning enhancing their capabilities. However, the lack of instruction-tuning datasets in languages other than English limits their application to diverse languages. To address this, researchers…
This paper addresses the challenge of detecting query variants—pairs of queries with identical intents. One application in commercial search engines is reformulating user queries with its variant online. While measuring pairwise query similarity has been an established standard, it often falls short…
Dense passage retrieval enhances Information Retrieval (IR) by encoding queries and passages into representation space. However, passage representations often fail to be referenced by their gold queries under domain shifts, revealing a weakness in representation space. One desirable concept for repr…
Mitigating positional bias of language models (LMs) for listwise inputs is a well-known and important problem (e.g., lost-in-the-middle). While zero-shot order-invariant LMs have been proposed to solve this issue, their success on practical listwise problems has been limited. In this work, as a firs…
Mixture-of-experts (MoEs) have been adopted for reducing inference costs by sparsely activating experts in large language models (LLMs). Despite these reductions, the massive number of parameters in MoEs still makes them expensive to serve. Conventionally, unstructured or structured pruning has been…
Adaptive Computation in Transformers (ACT) has been pursued in two directions: efficiency- and performance-focused. We study performance-focused ACT, or PACT, which invests more computation on hard steps to improve performance, such as by adding forward passes. We first discuss beam search and hesit…
To achieve lifelong human-agent interaction, dialogue agents need to constantly memorize perceived information and properly retrieve it for response generation (RG). While prior studies focus on getting rid of outdated memories to improve retrieval quality, we argue that such memories provide rich,…
Prompt optimization (PO) generates prompts to guide Large Language Models (LLMs) in performing tasks. Existing methods, such as PromptAgent, rely on a single static prompt, which struggles with disjoint cases in complex tasks. Although MoP uses multiple prompts, it fails to account for variations in…
Neural retrieval models have emerged as an effective tool for information retrieval, but their performance suffers when there is a domain shift between training and test data distributions. Recent work aims to construct pseudo-training data for the target domain by generating domain-adapted pseudo-q…
This paper aims to extend the code generation capability of large language models (LLMs) to automatically manage comprehensive software requirements from given textual descriptions. Such requirements include both functional (i.e. achieving expected behavior for inputs) and non-functional (e.g., time…
As the scale of language models (LMs) continues to grow, there is a heightened interest in reducing the inference cost associated with these models. Mixture-of-Experts (MoEs) present an efficient alternative to dense models, while the existing methods to convert pretrained dense models to MoEs is li…
Recently, instruction-tuned large language models (LLMs) are showing prominent performance on various tasks, such as question answering. However, the majority of instruction-tuned LLMs are English-centric, which hinders their application to low-resource language QA. In this paper, we propose COde-Mi…
This paper presents Coffee-Gym, a comprehensive RL environment for training models that provide feedback on code editing. Coffee-Gym includes two major components: (1) Coffee, a dataset containing humans’ code edit traces for coding questions and human-written feedback for editing erroneous code; (2…
Multilingual pretrained language models (mPLMs) have been widely adopted in cross-lingual transfer, and code-mixing has demonstrated effectiveness across various tasks in the absence of target language data. Our contribution involves an in-depth investigation into the counterproductive nature of tra…
Pre-trained language models (PLMs) exhibit promise in retrieval tasks but struggle with out-of-domain data due to distribution shifts.Addressing this, generative domain adaptation (DA), known as GPL, tackles distribution shifts by generating pseudo queries and labels to train models for predicting q…
This paper studies the problem of information retrieval, to adapt to unseen tasks. Existing work generates synthetic queries from domain-specific documents to jointly train the retriever. However, the conventional query generator assumes the query as a question, thus failing to accommodate general s…
Advancements in dense retrieval models have brought ColBERT to prominence in Information Retrieval (IR) with its advanced interaction techniques.However, ColBERT is reported to frequently underperform in zero-shot scenarios, where traditional techniques such as BM25 still exceed it.Addressing this,…
In this study, we investigate the potential of language models (LMs) in aiding patients experiencing anomia, a difficulty identifying the names of items. Identifying the intended target item from patient’s circumlocution involves the two challenges of term failure and error. (1) The terms relevant t…
Recently, pre-trained language models (PLMs) have been increasingly adopted in spoken language understanding (SLU). However, automatic speech recognition (ASR) systems frequently produce inaccurate transcriptions, leading to noisy inputs for SLU models, which can significantly degrade their performa…
We propose ListT5, a novel reranking approach based on Fusion-in-Decoder (FiD) that handles multiple candidate passages at both train and inference time. We also introduce an efficient inference framework for listwise ranking based on m-ary tournament sort with output caching. We evaluate and compar…
Despite advancements in Large Language Models (LLMs), many complex tasks are not easily solved in a single inference step, requiring the use of agentic LLMs in interactive environments. However, agentic LLMs suffer from a phenomenon known as reasoning derailment, due to the indiscriminate incorporat…
Agents powered by large language models (LLMs) inherit important limitations, such as the restricted context length, dependency on human-engineered exemplars (e.g., for task decomposition), and insufficient generalization. To address these challenges, we propose RaDA, a novel planning method for Web…
Despite the success of multilingual pretrained language models (mPLMs) for tasks such as dependency parsing (DEP) or part-of-speech (POS) tagging, their coverage of 100s of languages is still limited, as most of the 6500+ languages remains “unseen”. To adapt mPLMs for including such unseen langs, ex…
End-to-end approaches have shown promising results for speech translation (ST), but they suffer from its data scarcity compared to machine translation (MT). To address this, progressive training has become a common practice, of using external MT data during the fine-tuning phase. Despite of its prev…
One of the fundamental goals in code search is to retrieve a functionally correct code for a given natural language query. As annotating for correctness requires executing test cases (i.e. obtaining execution feedback), existing code search training datasets approximate text-code co-occurrences as…
This paper studies the use of reinforcement learning for conditional text generation, which overcomes the limitation of the prevalent supervised maximum likelihood estimation approach. However, it still suffers from challenges including the large action space and the delayed reward, as the reward ca…
The curse of multilinguality in training multilingual pretrained language models (mPLMs) refers to the negative interference between languages, especially when the capacity is limited. While increasing the capacity may appear intuitive for overcoming this curse, it negatively affects both training a…
Dense retrieval has shown promising results in various information retrieval tasks, and hybrid retrieval, combined with the strength of sparse retrieval, has also been actively studied. A key challenge in hybrid retrieval is to make sparse and dense complementary to each other. Existing models have…
Instructional videos make learning knowledge more efficient, by providing a detailed multimodal context of each procedure in instruction.A unique challenge posed by instructional videos is key-object degeneracy, where any single modality fails to sufficiently capture the key objects referred to in t…
Real-world data often follow a long-tailed distribution with a high imbalance in the number of samples between classes. The problem with training from imbalanced data is that some background features, common to all classes, can be unobserved in classes with scarce samples. As a result, this backgrou…
Although multilingual pretrained models (mPLMs) enabled support of various natural language processing in diverse languages, its limited coverage of 100+ languages lets 6500+ languages remain ‘unseen’. One common approach for an unseen language is specializing the model for it as target, by performi…
Prompting has gained tremendous attention as an efficient method for the adaptation of large-scale language models. However, prompts often act against human intuition and report unstable performances, which has motivated methods that automatically find effective prompts. One popular approach is grad…
This paper studies the problem of open-domain question answering, with the aim of answering a diverse range of questions leveraging knowledge resources. Two types of sources, QA-pair and document corpora, have been actively leveraged with the following complementary strength. The former is highly pr…
To build open-domain chatbots that are able to use diverse communicative skills, we propose a novel framework BotsTalk, where multiple agents grounded to the specific target skills participate in a conversation to automatically annotate multi-skill dialogues. We further present Blended Skill BotsTal…
Despite the super-human accuracy of recent deep models in NLP tasks, their robustness is reportedly limited due to their reliance on spurious patterns. We thus aim to leverage contrastive learning and counterfactual augmentation for robustness. For augmentation, existing work either requires humans…
Deep learning for Information Retrieval (IR) requires a large amount of high-quality query-document relevance labels, but such labels are inherently sparse. Label smoothing redistributes some observed probability mass over unobserved instances, often uniformly, uninformed of the true distribution. I…
We study event understanding as a critical step towards visual commonsense tasks. Meanwhile, we argue that current object-based event understanding is purely likelihood-based, leading to incorrect event prediction, due to biased correlation between events and objects. We propose to mitigate such bia…
This paper introduces a simple yet effective data-centric approach for the task of improving persona-conditioned dialogue agents. Prior model-centric approaches unquestioningly depend on the raw crowdsourced benchmark datasets such as Persona-Chat. In contrast, we aim to fix annotation artifacts in…
In this paper, we propose to leverage the unique characteristics of dialogues sharing commonsense knowledge across participants, to resolve the difficulties in summarizing them. We present SICK, a framework that uses commonsense inferences as additional context. Compared to previous work that solely…
Commonsense reasoning systems should be able to generalize to diverse reasoning cases. However, most state-of-the-art approaches depend on expensive data annotations and overfit to a specific benchmark without learning how to perform general semantic reasoning. To overcome these drawbacks, zero-shot…
Despite the success of neural machine translation models, tensions between fluency of optimizing target language modeling and source-faithfulness remain as challenges. Previously, Conditional Bilingual Mutual Information (CBMI), a scoring metric for the importance of target sentences and tokens, was…
World models have improved the ability of reinforcement learning agents to operate in a sample efficient manner, by being trained to predict plausible changes in the underlying environment. As the core tasks of world models are future prediction and commonsense understanding, our claim is that pre-t…
Language models (LMs) have shown great potential as implicit knowledge bases (KBs). And for their practical use, knowledge in LMs need to be updated periodically. However, existing tasks to assess LMs’ efficacy as KBs do not adequately consider multiple large-scale updates. To this end, we first pro…
Embeddings, which compress information in raw text into semantics-preserving low-dimensional vectors, have been widely adopted for their efficacy. However, recent research has shown that embeddings can potentially leak private information about sensitive attributes of the text, and in some cases, ca…
This paper studies how to enhance the document representation for the bi-encoder approach in dense document retrieval. The bi-encoder, separately encoding a query and a document as a single vector, is favored for high efficiency in large-scale information retrieval, compared to more effective but co…
Code completion, which aims to predict the following code token(s) according to the code context, can improve the productivity of software development. Recent work has proved that statistical language modeling with transformers can greatly improve the performance in the code completion task via lear…
We study compositional generalization, which aims to generalize on unseen combinations of seen structural elements, for code search. Unlike existing approaches of partially pursuing this goal, we study how to extract structural elements, which we name a template that directly targets compositional g…
Active learning can be defined as iterations of data labeling, model training, and data acquisition, until sufficient labels are acquired. A traditional view of data acquisition is that, through iterations, knowledge from human labels and models is implicitly distilled to monotonically increase the…
This paper studies the bias problem of multi-hop question answering models, of answering correctly without correct reasoning. One way to robustify these models is by supervising to not only answer right, but also with right reasoning chains. An existing direction is to annotate reasoning chains to t…
This paper studies the keyphrase generation (KG) task for scenarios where structure plays an important role. For example, a scientific publication consists of a short title and a long body, where the title can be used for de-emphasizing unimportant details in the body. Similarly, for short social me…
This paper studies the task of commonsense inference, especially natural language inference (NLI) and causal inference (CI), requiring knowledge beyond what is stated in the input sentences. State-of-the-arts have been neural models powered with knowledge or contextual embeddings, for example BERT,…
In this paper, we study review generation given a set of attribute identifiers which are user ID, product ID and rating. This is a difficult subtask of natural language generation since models are limited to the given identifiers, without any specific descriptive information regarding the inputs, wh…