As pretraining scaling laws approach saturation, Test-Time Scaling (TTS) has emerged as an important direction for improving reasoning by allocating inference-time compute to a fixed model prior. Viewed at a high level, TTS reframes inference as search over a space of partial reasoning states. While Chain-of-Thought (CoT) exposes intermediate steps, common instantiations rely on single-trajectory decoding, limiting recovery from early errors and exploration. This survey systematizes recent progress in tree-search-based reasoning, viewing inference as instance-specific optimization rather than decoding. We trace the evolution from uninformed search to Monte Carlo Tree Search (MCTS), highlighting how sampling-based control supports principled exploration–exploitation trade-offs. To unify a fragmented literature, we introduce a Unified Design Space spanning search topology, evaluation signals, and control dynamics, and advocate a standardized compute-reporting abstraction to make compute–accuracy trade-offs explicit and comparable.

We present a novel approach for claim verification from tabular data documents. Recent LLM-based approaches either employ complex pretraining/fine-tuning or decompose verification into subtasks, often lacking comprehensive explanations and generalizability. To address these limitations, we propose a Multi-Agentic framework for Claim vErification (MACE) consisting of three specialized agents: Planner, Executor, and Verifier. Instead of elaborate fine-tuning, each agent employs a zero-shot Chain-of-Thought setup to perform its tasks. MACE produces interpretable verification traces, with the Planner generating explicit reasoning strategies, the Executor providing detailed computation steps, and the Verifier validating the logic. Experiments demonstrate that MACE achieves state-of-the-art (SOTA) performance on two datasets and performs on par with the best models on two others, while achieving 80–100% of best performance with substantially smaller models: 27–92B parameters versus 235B. This combination of competitive performance, memory efficiency, and transparent reasoning highlights our framework’s effectiveness.

Deep research (DR) systems are increasingly used for complex information-seeking tasks, but existing works mainly focus on generating reports and summaries. In contrast, many enterprise tasks instead require an agent to identify concrete workflows which is a sequence of action-steps. For example, rather than summarizing budgeting policies, an agent should be able to determine the steps needed to answer a question such as: "How do I request new headcount given a fixed budget?". Therefore, we introduce DRFLOW, a benchmark for evaluating personalized workflows predicted by agents from heterogeneous sources. Each task requires the agent to identify relevant evidence from scattered sources, then use that evidence to predict the correct action-step sequence for the user’s task. DRFLOW contains 100 tasks across five domains, with 1, 246 reference workflow steps grounded in more than 3, 900 sources. We define seven diagnostic metrics covering factual grounding, step recovery, structural ordering, condition resolution, and personalization. We further present DRFLOW-Agent (DRFA), a workflow-oriented reference agent to predict personalized workflow. We show that although DRFA improves over strong baseline agents (upto 10.02% average F1 score), there is substantial room for improvement remains across these workflow metrics, indicating that predicting complete and correct personalized workflows remains a challenging frontier for deep research.

Document-level Relation Extraction (RE) aims to extract relation triples from documents. Existing document-RE models typically rely on supervised learning which requires substantial labeled data. To alleviate the amount of human supervision, Self-training (ST) has prospered again in language understanding by augmenting the fine-tuning of big pre-trained models whenever labeled data is insufficient. However, existing ST methods in RE fail to tackle the challenge of long-tail relations. In this work, we propose DuRE, a novel ST framework to tackle these problems. DuRE jointly models RE classification and text generation as a dual process. In this way, our model could construct and utilize both pseudo text generated from given labels and pseudo labels predicted from available unlabeled text, which are gradually refined during the ST phase. We proposed a contrastive loss to leverage the signal of the RE classifier to improve generation quality. In addition, we propose a self-adaptive way to sample pseudo text from different relation classes. Experiments on two document-level RE tasks show that DuRE significantly boosts recall and F1 score with comparable precision, especially for long-tail relations against several strong baselines.

In this work, we utilize Large Language Models (LLMs) for a novel use case: constructing Performance Predictors (PP) that estimate the performance of specific deep neural network architectures on downstream tasks. We create PP prompts for LLMs, comprising (i) role descriptions, (ii) instructions for the LLM, (iii) hyperparameter definitions, and (iv) demonstrations presenting sample architectures with efficiency metrics and ‘training from scratch’ performance. In machine translation (MT) tasks, GPT-4 with our PP prompts (LLM-PP) achieves a SoTA mean absolute error and a slight degradation in rank correlation coefficient compared to baseline predictors. Additionally, we demonstrate that predictions from LLM-PP can be distilled to a compact regression model (LLM-Distill-PP), which surprisingly retains much of the performance of LLM-PP. This presents a cost-effective alternative for resource-intensive performance estimation. Specifically, for Neural Architecture Search (NAS), we introduce a Hybrid-Search algorithm (HS-NAS) employing LLM-Distill-PP for the initial search stages and reverting to the baseline predictor later. HS-NAS performs similarly to SoTA NAS, reducing search hours by approximately 50%, and in some cases, improving latency, GFLOPs, and model size. The code can be found at: https://github.com/UBC-NLP/llmas.

Weight-sharing supernets are crucial for performance estimation in cutting-edge neural architecture search (NAS) frameworks. Despite their ability to generate diverse subnetworks without retraining, the quality of these subnetworks is not guaranteed due to weight sharing. In NLP tasks like machine translation and pre-trained language modeling, there is a significant performance gap between supernet and training from scratch for the same model architecture, necessitating retraining post optimal architecture identification.This study introduces a solution called mixture-of-supernets, a generalized supernet formulation leveraging mixture-of-experts (MoE) to enhance supernet model expressiveness with minimal training overhead. Unlike conventional supernets, this method employs an architecture-based routing mechanism, enabling indirect sharing of model weights among subnetworks. This customization of weights for specific architectures, learned through gradient descent, minimizes retraining time, significantly enhancing training efficiency in NLP. The proposed method attains state-of-the-art (SoTA) performance in NAS for fast machine translation models, exhibiting a superior latency-BLEU tradeoff compared to HAT, the SoTA NAS framework for machine translation. Furthermore, it excels in NAS for building memory-efficient task-agnostic BERT models, surpassing NAS-BERT and AutoDistil across various model sizes. The code can be found at: https://github.com/UBC-NLP/MoS.

Prior works on detoxification are scattered in the sense that they do not cover all aspects of detoxification needed in a real-world scenario. Notably, prior works restrict the task of developing detoxification models to only a seen subset of platforms, leaving the question of how the models would perform on unseen platforms unexplored. Additionally, these works do not address non-detoxifiability, a phenomenon whereby the toxic text cannot be detoxified without altering the meaning. We propose DetoxLLM, the first comprehensive end-to-end detoxification framework, which attempts to alleviate the aforementioned limitations. We first introduce a cross-platform pseudo-parallel corpus applying multi-step data processing and generation strategies leveraging ChatGPT. We then train a suite of detoxification models with our cross-platform corpus. We show that our detoxification models outperform the SoTA model trained with human-annotated parallel corpus. We further introduce explanation to promote transparency and trustworthiness. DetoxLLM additionally offers a unique paraphrase detector especially dedicated for the detoxification task to tackle the non-detoxifiable cases. Through experimental analysis, we demonstrate the effectiveness of our cross-platform corpus and the robustness of DetoxLLM against adversarial toxicity.

Identification of stance has recently gained a lot of attention with the extreme growth of fake news and filter bubbles. Over the last decade, many feature-based and deep-learning approaches have been proposed to solve stance detection. However, almost none of the existing works focus on providing a meaningful explanation for their prediction. In this work, we study stance detection with an emphasis on generating explanations for the predicted stance by capturing the pivotal argumentative structure embedded in a document. We propose to build a stance tree that utilizes rhetorical parsing to construct an evidence tree and to use Dempster Shafer Theory to aggregate the evidence. Human studies show that our unsupervised technique of generating stance explanations outperforms the SOTA extractive summarization method in terms of informativeness, non-redundancy, coverage, and overall quality. Furthermore, experiments show that our explanation-based stance prediction excels or matches the performance of the SOTA model on various benchmark datasets.

In this work, we focus on the problem of distinguishing a human written news article from a news article that is created by manipulating entities in a human written news article (e.g., replacing entities with factually incorrect entities). Such manipulated articles can mislead the reader by posing as a human written news article. We propose a neural network based detector that detects manipulated news articles by reasoning about the facts mentioned in the article. Our proposed detector exploits factual knowledge via graph convolutional neural network along with the textual information in the news article. We also create challenging datasets for this task by considering various strategies to generate the new replacement entity (e.g., entity generation from GPT-2). In all the settings, our proposed model either matches or outperforms the state-of-the-art detector in terms of accuracy. Our code and data are available at https://github.com/UBC-NLP/manipulated_entity_detection.

Motivated by applications such as question answering, fact checking, and data integration, there is significant interest in constructing knowledge graphs by extracting information from unstructured information sources, particularly text documents. Knowledge graphs have emerged as a standard for structured knowledge representation, whereby entities and their inter-relations are represented and conveniently stored as (subject,predicate,object) triples in a graph that can be used to power various downstream applications. The proliferation of financial news sources reporting on companies, markets, currencies, and stocks presents an opportunity for extracting valuable knowledge about this crucial domain. In this paper, we focus on constructing a knowledge graph automatically by information extraction from a large corpus of financial news articles. For that purpose, we develop a high precision knowledge extraction pipeline tailored for the financial domain. This pipeline combines multiple information extraction techniques with a financial dictionary that we built, all working together to produce over 342,000 compact extractions from over 288,000 financial news articles, with a precision of 78% at the top-100 extractions. The extracted triples are stored in a knowledge graph making them readily available for use in downstream applications.