The manufacturing sector is increasingly adopting Multimodal Large Language Models (MLLMs) to move from low-level perception toward higher-level reasoning and decision support, yet current evaluations rarely reflect the fine-grained precision that real-world manufacturing demands. Progress is further hindered by data scarcity and a lack of fine-grained domain semantics in existing datasets. To bridge this gap, we introduce FORGE, a benchmark for three core quality-assurance tasks of discrete manufacturing: workpiece verification, structural surface inspection, and assembly verification. We first construct a high-quality multimodal dataset spanning real-world 2D images and 3D point clouds, annotated with fine-grained domain semantics such as standardized model numbers. We then evaluate 18 state-of-the-art MLLMs on these three tasks, revealing significant performance gaps. Counter to conventional understanding, our bottleneck analysis on five representative models indicates that visual grounding is not the primary limiting factor. Instead, insufficient domain-specific knowledge is the key bottleneck. Beyond evaluation, we show that our structured annotations can serve as an actionable training resource: supervised fine-tuning of a compact 3B-parameter model on our data yields up to 90.8% relative improvement in accuracy on held-out manufacturing scenarios, providing preliminary evidence for a practical pathway toward domain-adapted manufacturing MLLMs.

Deep Research (DR) systems iteratively plan, retrieve evidence, and synthesize long-form reports in response to complex, open-ended queries. Existing approaches suffer from context overload, role entanglement, and error propagation over long horizons, while the most capable DR systems remain locked behind massive proprietary models. We present DeepDiver-DR (DD-DR), a multi-agent framework that decomposes the DR process into three specialized roles—planner, information seeker, and writer—coordinated through a persistent, file-based shared workspace. Each role is further equipped with fine-grained, DR-specific tools. To support rigorous evaluation, we introduce RubricWrite-Bench (RW-Bench), a benchmark of 100 rubric-based writing queries with a two-phase assessment of global report quality and point-level rubric fulfillment. Experiments show that DD-DR (30B) establishes a new state of the art among models at the same parameter scale on the DeepResearch Bench, and achieves performance competitive with leading proprietary DR systems on RW-Bench. Ablations further confirm the contribution of the architectural components.

In recent years, the non-deterministic properties of language models have garnered considerable attention and have shown a significant influence on real-world applications. However, such properties remain under-explored in machine translation (MT), a complex, non-deterministic NLP task. In this study, we systematically evaluate modern MT systems and identify temperature-constrained Non-Deterministic MT (ND-MT) as a distinct phenomenon. Additionally, we demonstrate that ND-MT exhibits significant potential in addressing the multimodality issue that has long challenged MT research and provides higher-quality candidates than Deterministic MT (D-MT) under temperature constraints. However, ND-MT introduces new challenges in evaluating system performance. Specifically, the evaluation framework designed for D-MT fails to yield consistent evaluation results when applied to ND-MT. We further investigate this emerging challenge by evaluating state-of-the-art ND-MT systems using both lexical-based and semantic-based metrics at varying sampling sizes. The results reveal a Buckets Effect across these systems: the ranking of ND-MT systems is dominated by the worst-quality candidate translation, as shown by automatic evaluation metrics. To mitigate this issue, we propose ExpectoSample, a strategy that first identifies reliable metrics and then enables robust ND-MT system selection for real-world.

Existing NL2SQL systems face two critical limitations : (1) they rely on in-context learning with only correct examples, overlooking the rich signal in historical error–fix pairs that could guide more robust self-correction; and (2) test-time scaling (TTS) approaches often decompose questions arbitrarily, producing near-identical SQL candidates across runs and diminishing ensemble gains. Moreover, these methods suffer from a stark accuracy–efficiency trade-off: high performance demands excessive computation, while fast variants compromise quality. We present Memo-SQL, a training-free framework that addresses these issues through two simple ideas: structured decomposition and experience-aware self-correction. Instead of leaving decomposition to chance, we apply three clear strategies, entity-wise, hierarchical, and atomic sequential, to encourage diverse reasoning. For correction, we build a dynamic memory of both successful queries and historical error–fix pairs, and use retrieval-augmented prompting to bring relevant examples into context at inference time, no fine-tuning or external APIs required. On BIRD, Memo-SQL achieves 68.5% execution accuracy, setting a new state of the art among open, zero-fine-tuning methods, while using over 10× fewer resources than prior TTS approaches.

KV caching is essential for efficient autoregressive decoding, but its memory footprint grows linearly with context length and quickly becomes a bottleneck for long-context large language models (LLMs). We study whether feature-dimension compression can serve as an orthogonal second stage for KV-cache reduction, and introduce AURA-KV, an adaptive-rank subspace approximation method for KV caches. AURA-KV is training-free: it decomposes post-RoPE key and value caches into compact bases and coefficients, supports incremental decoding, and allocates rank adaptively across layers under a global memory budget. Because it compresses the feature dimension rather than selecting tokens or lowering precision, it can be combined with token eviction and quantization methods. Across LongBench, RULER, and InfiniteBench, AURA-KV preserves long-context performance on Llama-3-8B, Mistral-7B, and LongChat-7B under moderate compression and degrades gracefully under more aggressive budgets. In latency measurements, AURA-KV improves per-layer decoding speed by up to 2.75 ×, and by up to 3.23 × when combined with token-level cache reduction, with a small one-time prefill overhead.

Instruction-guided speech editing requires a model to modify specified speech attributes while preserving non-target characteristics. Despite rapid progress in Speech Large Language Models (Speech LLMs), systematic evaluation of this capability remains challenging, as existing benchmarks are fragmented across isolated editing tasks. To bridge this gap, we introduce **SpeechEditBench**, a bilingual multi-attribute benchmark for instruction-guided speech editing. SpeechEditBench encompasses seven atomic editing tasks, as well as compositional editing tasks that integrate multiple operations within a single instruction. We propose an anchor-based evaluation protocol that separately assesses the edit success of target attributes and the preservation of non-target linguistic content, leading to three metrics: target success, preservation success, and joint success. Using this benchmark, we evaluate mainstream Speech LLMs and specialized speech editing systems. The results reveal three key findings: (1) no single model performs well across all editing dimensions; (2) closed-source Speech LLMs generally outperform open-source models; (3) compositional editing poses a significant challenge, with even the most advanced models struggling to achieve high joint success. SpeechEditBench provides a rigorous diagnostic framework to identify bottlenecks in Speech LLMs, thereby facilitating the development of next-generation models with more precise instruction-guided editing capabilities. Data and code are available at https://github.com/daxintan-cuhk/SpeechEditBench.

Recent advances in large language models have led to numerous task-specialized fine-tuned variants, creating a need for efficient model merging techniques that preserve specialized capabilities while avoiding costly retraining. While existing task vector-based merging methods show promise, they typically apply uniform coefficients across all parameters, overlooking varying parameter importance both within and across tasks. We present Sens-Merging, a sensitivity-guided coefficient adjustment method that enhances existing model merging techniques by operating at both task-specific and cross-task levels. Our method analyzes parameter sensitivity within individual tasks and evaluates cross-task transferability to determine optimal merging coefficients. Extensive experiments on Mistral 7B and LLaMA2 7B/13B models demonstrate that Sens-Merging significantly improves performance across general knowledge, mathematical reasoning, and code generation tasks. Notably, when combined with existing merging techniques, our method enables merged models to outperform specialized fine-tuned models, particularly in code generation tasks. Our findings reveal important trade-offs between task-specific and cross-task scalings, providing insights for future model merging strategies.

Recent advances in reasoning with large language models (LLMs) have popularized Long Chain-of-Thought (LCoT), a strategy that encourages deliberate and step-by-step reasoning before producing a final answer. While LCoTs have enabled expert-level performance in complex tasks, how the internal structures of their reasoning chains drive, or even predict, the correctness of final answers remains a critical yet underexplored question. In this work, we present LCoT2Tree, an automated framework that converts sequential LCoTs into hierarchical tree structures and thus enables deeper structural analysis of LLM reasoning. Using graph neural networks (GNNs), we reveal that structural patterns extracted by LCoT2Tree, including exploration, backtracking, and verification, serve as stronger predictors of final performance across a wide range of tasks and models. Leveraging an explainability technique, we further identify critical thought patterns such as over-branching that account for failures. Beyond diagnostic insights, the structural patterns by LCoT2Tree support practical applications, including improving Best-of-N decoding effectiveness. Overall, our results underscore the critical role of internal structures of reasoning chains, positioning LCoT2Tree as a powerful tool for diagnosing, interpreting, and improving reasoning in LLMs.

In this paper, we study parameter-efficient fine-tuning methods for large pre-trained models. Specifically, we improve LoRA approaches to alleviate the performance loss from the constrained adapter by introducing a non-linear transformation (call it LoRAN). For a better adaptation, we also design a new non-linear function to appropriately fit the accumulated weight updates. We test our method in multiple advanced large language models. Experimental results show that our LoRAN significantly outperforms a strong baseline on SAMSum and 20 Newsgroups tasks. Moreover, when a lower rank is applied, our approach even yields a 1.95-point improvement in the classification task.

LLMs have marked a revolutonary shift, yet they falter when faced with compositional reasoning tasks. Our research embarks on a quest to uncover the root causes of compositional reasoning failures of LLMs, uncovering that most of them stem from the improperly generated or leveraged implicit reasoning results. Inspired by our empirical findings, we resort to Logit Lens and an intervention experiment to dissect the inner hidden states of LLMs. This deep dive reveals that implicit reasoning results indeed surface within middle layers and play a causative role in shaping the final explicit reasoning results. Our exploration further locates multi-head self-attention (MHSA) modules within these layers, which emerge as the linchpins in accurate generation and leveraing of implicit reasoning results. Grounded on the above findings, we develop CREME, a lightweight method to patch errors in compositional reasoning via editing the located MHSA modules. Our empirical evidence stands testament to CREME’s effectiveness, paving the way for autonomously and continuously enhancing compositional reasoning capabilities in language models.

Large Language Models (LLMs) have shown human-like reasoning abilities but still face challenges in solving complex logical problems. Existing unidirectional chaining methods, such as forward chaining and backward chaining, suffer from issues like low prediction accuracy and efficiency. To address these, we propose a bidirectional chaining method, Bi-Chainer, which dynamically switches to depth-first reasoning in the opposite reasoning direction when it encounters multiple branching options within the current direction. Thus, the intermediate reasoning results can be utilized as guidance to facilitate the reasoning process. We show that Bi-Chainer achieves sizable accuracy boots over unidirectional chaining frameworks on four challenging logical reasoning datasets. Moreover, Bi-Chainer enhances the accuracy of intermediate proof steps and reduces the average number of inference calls, resulting in more efficient and accurate reasoning.

Large Language Models (LLMs) have recently revolutionized the NLP field, while they still fall short in some specific down-stream tasks. In the work, we focus on utilizing LLMs to perform machine translation, where we observe that two patterns of errors frequently occur and drastically affect the translation quality: language mismatch and repetition. The work sets out to explore the potential for mitigating these two issues by leveraging model editing methods, e.g., by locating Feed-Forward Network (FFN) neurons or something that are responsible for the errors and deactivating them in the inference time.We find that directly applying such methods either limited effect on the targeted errors or has significant negative side-effect on the general translation quality, indicating that the located components may also be crucial for ensuring machine translation with LLMs on the rails.To this end, we propose to refine the located components by fetching the intersection of the locating results under different language settings, filtering out the aforementioned information that is irrelevant to targeted errors. The experiment results empirically demonstrate that our methods can effectively reduce the language mismatch and repetition ratios and meanwhile enhance or keep the general translation quality in most cases.

In this study, we delve into the realm of counterfactual reasoning capabilities of large language models (LLMs). Our primary objective is to cultivate the counterfactual thought processes within LLMs and rigorously assess these processes for their validity. Specifically, we introduce a novel task, Counterfactual Logical Modification (CLOMO), and a high-quality human-annotated benchmark. In this task, LLMs must adeptly alter a given argumentative text to uphold a predetermined logical relationship. To effectively evaluate a generation model’s counterfactual capabilities, we propose an innovative evaluation metric, the decomposed Self-Evaluation Score (SES) to directly evaluate the natural language output of LLMs instead of modeling the task as a multiple-choice problem. Analysis shows that the proposed automatic metric aligns well with human preference. Our experimental results show that while LLMs demonstrate a notable capacity for logical counterfactual thinking, there remains a discernible gap between their current abilities and human performance. Code and data are available at https://github.com/Eleanor-H/CLOMO.

Large Language Models (LLMs) have succeeded remarkably in understanding long-form contents. However, exploring their capability for generating long-form contents, such as reports and articles, has been relatively unexplored and inadequately assessed by existing benchmarks. The prevalent evaluation methods, which predominantly rely on crowdsourcing, are recognized for their labor-intensive nature and lack of efficiency, whereas automated metrics, such as the ROUGE score, demonstrate discordance with human judgment criteria. In this paper, we propose ProxyQA, an innovative framework dedicated to assessing long-text generation. ProxyQA comprises in-depth human-curated meta-questions spanning various domains, each accompanied by specific proxy-questions with pre-annotated answers. LLMs are tasked to generate extensive content in response to these meta-questions, by engaging an evaluator and incorporating the generated texts as contextual background, ProxyQA assesses the generated content’s quality through the evaluator’s accuracy in addressing the proxy-questions. We examine multiple LLMs, emphasizing ProxyQA’s demanding nature as a high-quality assessment tool. Human evaluation demonstrates that the proxy-question method is notably self-consistent and aligns closely with human evaluative standards. The dataset and leaderboard is available at https://proxy-qa.com.

Compositional generalization, representing the model’s ability to generate text with new attribute combinations obtained by recombining single attributes from the training data, is a crucial property for multi-aspect controllable text generation (MCTG) methods. Nonetheless, a comprehensive compositional generalization evaluation benchmark of MCTG is still lacking. We propose CompMCTG, a benchmark encompassing diverse multi-aspect labeled datasets and a crafted three-dimensional evaluation protocol, to holistically evaluate the compositional generalization of MCTG approaches. We observe that existing MCTG works generally confront a noticeable performance drop in compositional testing. To mitigate this issue, we introduce Meta-MCTG, a training framework incorporating meta-learning, where we enable models to learn how to generalize by simulating compositional generalization scenarios in the training phase. We demonstrate the effectiveness of Meta-MCTG through achieving obvious improvement (by at most 3.64%) for compositional testing performance in 94.4%.

Compared to news and chat summarization, the development of meeting summarization is hugely decelerated by the limited data. To this end, we introduce a versatile Chinese meeting summarization dataset, dubbed VCSum, consisting of 239 real-life meetings, with a total duration of over 230 hours. We claim our dataset is versatile because we provide the annotations of topic segmentation, headlines, segmentation summaries, overall meeting summaries, and salient sentences for each meeting transcript. As such, the dataset can adapt to various summarization tasks or methods, including segmentation-based summarization, multi-granularity summarization and retrieval-then-generate summarization. Our analysis confirms the effectiveness and robustness of VCSum. We also provide a set of benchmark models regarding different downstream summarization tasks on VCSum to facilitate further research.

Meetings typically involve multiple participants and lengthy conversations, resulting in redundant and trivial content. To overcome these challenges, we propose a two-step framework, Reconstruct before Summarize (RbS), for effective and efficient meeting summarization. RbS first leverages a self-supervised paradigm to annotate essential contents by reconstructing the meeting transcripts. Secondly, we propose a relative positional bucketing (RPB) algorithm to equip (conventional) summarization models to generate the summary. Despite the additional reconstruction process, our proposed RPB significantly compresses the input, leading to faster processing and reduced memory consumption compared to traditional summarization methods. We validate the effectiveness and efficiency of our method through extensive evaluations and analyses. On two meeting summarization datasets, AMI and ICSI, our approach outperforms previous state-of-the-art approaches without relying on large-scale pre-training or expert-grade annotating tools.

General-purpose text decoding approaches are usually adopted for dialogue response generation. Although the quality of the generated responses can be improved with dialogue-specific encoding methods, conversational decoding methods are still under-explored. Inspired by SimDRC that a good dialogue feature space should follow the rules of locality and isotropy, we present a fine-grained conversational decoding method, termed isotropic and proximal search (IPS). Our method is designed to generate the semantic-concentrated response, while still maintaining informativeness and discrimination against the context. Experiments show that our approach significantly outperforms existing decoding strategies in the dialogue field across both automatic and human evaluation metrics. More in-depth analyses further confirm the effectiveness of our approach.

While conversational semantic role labeling (CSRL) has shown its usefulness on Chinese conversational tasks, it is still under-explored in non-Chinese languages due to the lack of multilingual CSRL annotations for the parser training. To avoid expensive data collection and error-propagation of translation-based methods, we present a simple but effective approach to perform zero-shot cross-lingual CSRL.Our model implicitly learns language-agnostic, conversational structure-aware and semantically rich representations with the hierarchical encoders and elaborately designed pre-training objectives. Experimental results show that our model outperforms all baselines by large margins on two newly collected English CSRL test sets. More importantly, we confirm the usefulness of CSRL to non-Chinese conversational tasks such as the question-in-context rewriting task in English and the multi-turn dialogue response generation tasks in English, German and Japanese by incorporating the CSRL information into the downstream conversation-based models. We believe this finding is significant and will facilitate the research of non-Chinese dialogue tasks which suffer the problems of ellipsis and anaphora.

Contrastive learning has shown great potential in unsupervised sentence embedding tasks, e.g., SimCSE (CITATION).However, these existing solutions are heavily affected by superficial features like the length of sentences or syntactic structures. In this paper, we propose a semantic-aware contrastive learning framework for sentence embeddings, termed Pseudo-Token BERT (PT-BERT), which is able to explore the pseudo-token space (i.e., latent semantic space) representation of a sentence while eliminating the impact of superficial features such as sentence length and syntax. Specifically, we introduce an additional pseudo token embedding layer independent of the BERT encoder to map each sentence into a sequence of pseudo tokens in a fixed length. Leveraging these pseudo sequences, we are able to construct same-length positive and negative pairs based on the attention mechanism to perform contrastive learning. In addition, we utilize both the gradient-updating and momentum-updating encoders to encode instances while dynamically maintaining an additional queue to store the representation of sentence embeddings, enhancing the encoder’s learning performance for negative examples. Experiments show that our model outperforms the state-of-the-art baselines on six standard semantic textual similarity (STS) tasks. Furthermore, experiments on alignments and uniformity losses, as well as hard examples with different sentence lengths and syntax, consistently verify the effectiveness of our method.

Conversational semantic role labeling (CSRL) is believed to be a crucial step towards dialogue understanding. However, it remains a major challenge for existing CSRL parser to handle conversational structural information. In this paper, we present a simple and effective architecture for CSRL which aims to address this problem. Our model is based on a conversational structure aware graph network which explicitly encodes the speaker dependent information. We also propose a multi-task learning method to further improve the model. Experimental results on benchmark datasets show that our model with our proposed training objectives significantly outperforms previous baselines.

Language models like BERT and SpanBERT pretrained on open-domain data have obtained impressive gains on various NLP tasks. In this paper, we probe the effectiveness of domain-adaptive pretraining objectives on downstream tasks. In particular, three objectives, including a novel objective focusing on modeling predicate-argument relations, are evaluated on two challenging dialogue understanding tasks. Experimental results demonstrate that domain-adaptive pretraining with proper objectives can significantly improve the performance of a strong baseline on these tasks, achieving the new state-of-the-art performances.

For multi-turn dialogue rewriting, the capacity of effectively modeling the linguistic knowledge in dialog context and getting ride of the noises is essential to improve its performance. Existing attentive models attend to all words without prior focus, which results in inaccurate concentration on some dispensable words. In this paper, we propose to use semantic role labeling (SRL), which highlights the core semantic information of who did what to whom, to provide additional guidance for the rewriter model. Experiments show that this information significantly improves a RoBERTa-based model that already outperforms previous state-of-the-art systems.