论文检索

Abdelrahman Abdallah, Mohammed Ali, Bhawna Piryani, Adam Jatowt

Although Large Language Models (LLMs) show strong potential for zero-shot document ranking, current listwise approaches face three critical limitations. First, context length constraints prevent processing many documents simultaneously. Second, sequential generation creates bottlenecks that cannot run in parallel. Third, ranking results depend heavily on initial document order, leading to inconsistent performance. We introduce BracketRank, a reasoning-driven competitive elimination framework that addresses these challenges through systematic group competition. Our method uses adaptive grouping to automatically optimise group sizes based on LLM context limits, reasoning-enhanced prompts that require explicit relevance explanations, and bracket-style elimination where documents compete through winner and loser brackets. This structure ensures every document has fair advancement opportunities regardless of initial positioning while allowing for parallel processing across competition stages. We evaluate BracketRank on TREC DL 19, TREC DL 20, and eight BEIR benchmark datasets. Results show that BracketRank achieves 77.90 NDCG@5 on TREC DL 19 and 75.85 NDCG@5 on TREC DL 20, outperforming RankGPT and other state-of-the-art methods. On BEIR datasets, BracketRank reaches 54.66 average NDCG@10, demonstrating robust performance across diverse domains.

Guangya Wan, Mingyang Ling, Xiaoqi Ren, Rujun Han, Sheng Li, Zizhao Zhang

Long-horizon tasks that require sustained reasoning and multiple tool interactions remain challenging for LLM agents: small errors compound across steps, and even state-of-the-art models often hallucinate or lose coherence. We identify context management as the central bottleneck—extended histories cause agents to overlook critical evidence or become distracted by irrelevant information, thus failing to replan or reflect from previous mistakes. To address this, we propose COMPASS (Context-Organized Multi-Agent Planning and Strategy System), a lightweight hierarchical framework that separates tactical execution, strategic oversight, and context organization into three specialized components: (1) a Main Agent that performs reasoning and tool use, (2) a Meta-Thinker that monitors progress and issues strategic interventions, and (3) a Context Manager that maintains concise, relevant progress briefs for different reasoning stages. Across three challenging benchmarks—GAIA, BrowseComp, and Humanity’s Last Exam—COMPASS improves accuracy by up to 20% relative to both single- and multi-agent baselines. We further introduce a test-time scaling extension that elevates performance to match established DeepResearch agents, and a post-training pipeline that delegates context management to smaller models for enhanced efficiency.

Nikita Tatarinov, Vidhyakshaya Kannan, Haricharana Srinivasa, Arnav Raj, Harpreet Singh Anand, Varun Singh, Aditya Luthra, Ravij Lade, Agam Shah, Sudheer Chava

We introduce KG-MuLQA (Knowledge-Graph-based Multi-Level Question-Answer Extraction): a framework that (1) extracts QA pairs at multiple complexity levels (2) along three key dimensions – multi-hop retrieval, set operations, and answer plurality, (3) by leveraging knowledge-graph-based document representations. This approach enables fine-grained assessment of model performance across controlled difficulty levels. Using this framework, we construct a dataset of 20,139 QA pairs based on financial credit agreements and evaluate 16 proprietary and open-weight Large Language Models, observing that even the best-performing models struggle with set-based comparisons and multi-hop reasoning over long contexts. Our analysis reveals systematic failure modes tied to semantic misinterpretation and inability to handle implicit relations.

Jinu Lee, Kyoung-Woon On, Sophia Simeng Han, Arman Cohan, Julia Hockenmaier

Evaluating the quality of LLM-generated reasoning traces in expert domains (e.g., law) is essential for ensuring credibility and explainability, yet remains challenging due to the inherent complexity of such reasoning tasks. We introduce LEGIT (LEGal Issue Trees), a novel large-scale (24K instances) expert-level legal reasoning dataset with an emphasis on reasoning trace evaluation. We convert court judgments into hierarchical trees of opposing parties’ arguments and the court’s conclusions, which serve as rubrics for evaluating the issue coverage and correctness of the reasoning traces. We verify the reliability of these rubrics via human expert annotations and comparison with coarse, less informative rubrics. Using the LEGIT dataset, we show that (1) LLMs’ legal reasoning ability is seriously affected by both legal issue coverage and correctness, and that (2) retrieval-augmented generation (RAG) and RL with rubrics bring complementary benefits for legal reasoning abilities, where RAG improves overall reasoning capability, whereas RL improves correctness albeit with reduced coverage.

Adarsh Singh, Kushal Raj Bhandari, Jianxi Gao, Soham Dan, Vivek Gupta

Open-Domain Table Question Answering (TQA) involves retrieving relevant tables from a large corpus to answer natural language queries. Traditional dense retrieval models, such as DTR and DPR, not only incur high computational costs for large-scale retrieval tasks but also require retraining or fine-tuning on new datasets, limiting their adaptability to evolving domains and knowledge. In this work, we propose **CRAFT**, a zero-shot, cascaded retrieval approach that first uses a sparse retrieval model to filter a subset of candidate tables before applying more computationally expensive dense models as re-rankers.To improve retrieval quality, we enrich table representations with descriptive titles and summaries generated by *Gemini Flash 1.5*, enabling richer semantic matching between queries and tabular structures. Our method outperforms state-of-the-art (SOTA) sparse, dense, and hybrid retrievers on the NQ-Tables dataset. It also demonstrates strong zero-shot performance on the more challenging OTT-QA benchmark, achieving competitive results at higher recall thresholds, where the task requires multi-hop reasoning across both textual passages and relational tables.This work establishes a scalable and adaptable paradigm for table retrieval, bridging the gap between fine-tuned architectures and lightweight, plug-and-play retrieval systems. Code and data are available at: [https://coral-lab-asu.github.io/CRAFT/](https://coral-lab-asu.github.io/CRAFT/)

Zhenhua Liu, Lijun Li, Ruizhe Chen, Yuxian Jiang, Tong Zhu, Zhaochen Su, Wenliang Chen, Jing Shao

While guided decoding, especially value-guided methods, has emerged as a cost-effective alternative for controlling language model outputs without re-training models, its effectiveness is limited by the accuracy of the value function. We identify that this inaccuracy stems from a core distributional gap: existing methods train static value functions on trajectories sampled exclusively from the base policy, which inherently confines their training to a narrow and suboptimal view of the potential output space. We propose Iterative Value Refinement, a novel framework designed to bridge this gap. It employs Value Exploration to provide a more comprehensive and robust training signal, complemented by Iterative Self-Refinement, which uses the improved value function from one iteration to guide the generation of higher-quality data for the next. Extensive experiments on text summarization, multi-turn dialogue, and instruction following demonstrate the effectiveness of our framework in aligning language models. Our approach not only achieves alignment but also significantly reduces computational costs by leveraging principled value function optimization for efficient and effective control.

Yupeng Hou, Jiacheng Li, Xiangjun Fu, Zhankui He, An Yan, Xiusi Chen, Julian McAuley

Feature engineering has long been central to recommender systems, yet effectively leveraging textual item features remains challenging. Recent advances in large language models (LLMs) have enabled their use as semantic encoders for recommendation, but their roles and behaviors in this setting are still not well understood. Prior studies often rely on general-purpose embedding benchmarks (e.g., MTEB) when selecting LLMs, overlooking the unique characteristics of recommendation tasks. To address this gap, we introduce BLaIR, a comprehensive benchmark for evaluating LLMs as semantic encoders in recommendation scenarios. We contribute (1) a new large-scale Amazon Reviews 2023 dataset with over 570 million reviews and 48 million items, (2) a unified benchmark covering sequential recommendation, collaborative filtering, and product search, and (3) a new complex-query product search task featuring both semi-synthetic and real-world evaluation datasets. Experiments with 11 leading LLMs show that their rankings on BLaIR show little correlation with MTEB, highlighting the unique challenges of semantic encoding in recommendation.

Zhengxiang Cheng, Dongping Chen, Mingyang Fu, Tianyi Zhou

Large Reasoning Models (LRMs) have achieved remarkable success, yet they often suffer from producing unnecessary and verbose reasoning chains. We identify a core aspect of this issue as ”invalid thinking”— models tend to repeatedly double-check their work after having derived the correct answer. To address this specific inefficiency, we move beyond the general principles of Efficacy and Efficiency to propose two new, fine-grained principles: Brevity, which advocates for eliminating redundancy, and Sufficiency, which ensures critical reasoning steps are preserved. Guided by these principles, we introduce LC-R1, a post-training method based on Group Relative Policy Optimization (GRPO). LC-R1 employs a novel combination of a Length Reward for overall conciseness and a Compress Reward that is specifically designed to remove the invalid portion of the thinking process. Extensive experiments on multiple reasoning benchmarks demonstrate that LC-R1 achieves a significant reduction in sequence length (5̃0%) with only a marginal (2̃%) drop in accuracy, achieving a favorable trade-off point on the Pareto frontier that prioritizes high compression. Our analysis further validates the robustness of LC-R1 and provides valuable insights for developing more powerful yet computationally efficient LRMs.

Dahyun Jung, Jaewook Lee, Heuiseok Lim

Large language models (LLMs) require frequent knowledge updates to reflect changing facts and mitigate hallucinations. To meet this demand, lifelong knowledge editing has emerged as a continual approach to modify specific pieces of knowledge without retraining the entire model. Existing parameter-editing methods struggle with stability during sequential edits due to catastrophic forgetting. While retrieval-based approaches are proposed to alleviate this issue, their applicability remains limited across various datasets because of high training costs. To address these limitations and enhance scalability in lifelong settings, we propose LightEdit. Our framework first selects relevant knowledge from retrieved information to modify the query effectively. It then incorporates a decoding strategy to suppress the model’s original knowledge probabilities, thereby enabling efficient edits based on the selected information. Extensive experiments on ZSRE, Counterfact, and RIPE benchmarks demonstrate that LightEdit outperforms existing lifelong knowledge editing methods. Furthermore, by minimizing training costs, LightEdit achieves cost-effective scalability, enabling easy adaptation to various datasets.

Jason S Lucas, Matt Murtagh White, Ali Al-Lawati, Uchendu Uchendu, Adaku Uchendu, Dongwon Lee

Harmful content detectors—particularly disinformation classifiers—are predominantly developed and evaluated on Standard American English (), leaving their robustness to dialectal variation unexplored. We present , the first benchmark for evaluating disinformation detection robustness across 50 English dialects spanning U.S., British, African, Caribbean, and Asia-Pacific varieties. Using Multi-VALUE’s linguistically-grounded transformations, we introduce D-CUBE (Dialectal Disinformation Detection Corpus), a core corpus component of comprising 195K samples derived from established disinformation benchmarks. Our evaluation of 16 detection models reveals systematic vulnerabilities: human-written dialectal content degrades detection by 1.4–3.6% F1, while AI-generated content remains stable. Fine-tuned transformers substantially outperform zero-shot LLMs (96.6% vs. 78.3% best-case F1), with some models exhibiting catastrophic failures exceeding 33% degradation on mixed content. Cross-dialectal transfer analysis across 2,450 dialect pairs shows that multilingual models (mDeBERTa: 97.2% average F1) generalize effectively, while monolingual models like RoBERTa and XLM-RoBERTa fail on dialectal inputs. These findings demonstrate that current disinformation detectors may systematically disadvantage hundreds of millions of non- speakers worldwide. We release the benchmark, including the , and evaluation tools.

Junyi Li, Yongqiang Chen, Ningning Ding

Machine unlearning has gained increasing attention in recent years, as a promising technique to selectively remove unwanted privacy or copyrighted information from Large Language Models that are trained on a massive scale of human data. However, the emergence of Large Reasoning Models (LRMs), which emphasize long chain-of-thought (CoT) reasoning to address complex questions, presents a dilemma to unlearning: existing methods either struggle to completely eliminate undesired knowledge from the CoT traces or degrade the reasoning performances due to the interference with the reasoning process. To this end, we introduce Counterfactual Unlearning through iterative Preference Optimization (CiPO), a novel framework that redefines unlearning as the targeted intervention of the CoT reasoning in LRMs. More specifically, given a desired unlearning target answer, CiPO instructs LRMs to generate a logically valid counterfactual reasoning trace for preference tuning. As the LRM adjusts to the counterfactual trace, CiPO iteratively updates the preference learning data to increase the discrepancy from the original model. This iterative loop ensures both desirable unlearning and smooth optimization, effectively mitigating the dilemma. Experiments on challenging benchmarks demonstrate that CiPO excels at unlearning, completely removing knowledge from both the intermediate CoT steps and the final answer, while preserving the reasoning abilities of LRMs.

Kevin Du, Clara Kümpel, Michelle Wastl, Alex Warstadt

Users frequently express their beliefs to large language models (LLMs). In some situations, the LLM should accept these contextual beliefs as true. In others, they should stick to their prior knowledge. Notably, users’ expressions of belief (EoBs) can take linguistically diverse forms—using presuppositions, evidential and certainty markers, or varied tones—each of which may have a different persuasiveness over the LLMs. We introduce a typology to systematically evaluate how different EoBs affect whether models follow context versus prior knowledge. The typology is grounded in four linguistically motivated dimensions: form, evidentiality, epistemic stance, and tone, spanning 17 fine-grained types. By pairing these EoBs with world knowledge facts, we generate controlled EoB–query pairs that isolate the effect of linguistic variation. Using this benchmark, we evaluate 16 LLMs that differ in architecture (Llama3, Qwen3, Gemma3), scale (1B-30B parameters), and training stages (base vs instruct). We identify meaningful variations in response behavior across these axes, e.g., that bigger models and instruction models tend to be less context–following than smaller models and base models. We further identify specific EoBs that statistically significantly persuade LMs more consistently than others. Our work reveals systematic patterns in how linguistic framing affects LLM context integration, with implications for prompt engineering and model robustness.

Diana Abagyan, Alejandro R. Salamanca, Andres Felipe Cruz-Salinas, Kris Cao, Hangyu Lin, Acyr Locatelli, Marzieh Fadaee, Ahmet Üstün, Sara Hooker

Pretraining massively multilingual Large Language Models (LLMs) for many languages at once is challenging due to limited model capacity, scarce high-quality data, and compute constraints. Moreover, the lack of language coverage in the tokenizer makes it harder to address the gap for new languages purely at the post-training stage. In this work, we study what relatively cheap interventions early on in training improve *language plasticity*, or adaptation capabilities of the model post-training to new languages. We focus on tokenizer design and propose using a *universal* tokenizer that is trained for more languages than the primary pretraining languages to enable efficient adaptation in expanding language coverage after pretraining. Our systematic experiments across diverse groups of languages and different training strategies show that a universal tokenizer enables significantly higher language adaptation, with up to 20.2% increase in win rates compared to tokenizers specific to pretraining languages. Furthermore, a universal tokenizer also leads to better plasticity towards languages that are completely unseen in the tokenizer and pretraining, by up to 5% win rate gain. We achieve this adaptation to an expanded set of languages with minimal compromise in performance on the majority of languages included in pretraining.

Zhihao Gong, Zeyu Sun, Dong Huang, Qingyuan Liang, Jie M. Zhang, Dan Hao

While Large Language Models (LLMs) have substantially improved the functional correctness of code translation, the critical dimension of execution efficiency remains overlooked. We present Trace, the first benchmark to explicitly assess efficiency in LLM-translated code. Trace includes 1,000 efficiency-critical tasks across C++, Java, and Python, each augmented with stress tests that reveal efficiency disparities often overlooked by small-scale tests. Using Trace, we conduct an extensive evaluation of 28 representative LLMs and highlight several key insights: 1) Correctness and efficiency are often misaligned: the correctness leader Claude-Sonnet-4-Think achieves only moderate time efficiency, outperformed by smaller open-source LLMs such as Qwen2.5-Coder-14B-Instruct. 2) Inefficiency is both prevalent and patterned: 23.5% of correct translations suffer from notable inefficiency, mainly arising from algorithm implementation discrepancy (11.9%), language construct mismatch (66.4%), and resource management inefficiency (21.7%).3) Inference-time prompt strategies bring only modest improvements, indicating that simple prompting alone is insufficient to improve translation efficiency. Together, our results establish execution efficiency as an essential dimension of code translation and position Trace as a principled foundation for efficiency-oriented evaluation. Our code and data are available at: https://github.com/Albert-Gong/TRACE.

Zhongyuan Peng, Yifan Yao, Kaijing Ma, Shuyue Guo, Yizhe Li, Yichi Zhang, Chenchen Zhang, Yifan Zhang, Zhouliang Yu, Luming Li 等

Translating natural language mathematical statements into formal, executable code is a fundamental challenge in automated theorem proving. While prior work has focused on generation and compilation success, little attention has been paid to the critic phase—the evaluation of whether generated formalizations truly capture the semantic intent of the original problem. In this paper, we introduce CriticLean, a novel critic-guided reinforcement learning framework that elevates the role of the critic from a passive validator to an active learning component. Specifically, first, we propose the CriticLeanGPT, trained via supervised fine-tuning and reinforcement learning, to rigorously assess the semantic fidelity of Lean 4 formalizations. Then, we introduce CriticLeanBench, a benchmark designed to measure models’ ability to distinguish semantically correct from incorrect formalizations, and demonstrate that our trained CriticLeanGPT models can significantly outperform strong open- and closed-source baselines. Building on the CriticLean framework, we construct FineLeanCorpus, a dataset comprising over 509K problems that exhibits rich domain diversity, broad difficulty coverage, and high correctness based on human evaluation.Overall, our findings highlight that optimizing the critic phase is essential for producing reliable formalizations and we hope our CriticLean will provide valuable insights for future advances in formal mathematical reasoning.

Wenxi Chen, Ruiqi Yan, Yushen Chen, Zhikang Niu, Ziyang Ma, Xiquan Li, Yuzhe Liang, Wenhanlin, Shunshun Yin, Ming Tao 等

Speech codecs that convert continuous speech signals into discrete tokens have become essential for speech language models. However, existing codecs struggle to balance high-quality reconstruction with semantically rich representations, limiting their effectiveness in both generative and understanding tasks. In this work, we propose \textbf{SAC}, a neural speech codec with semantic-acoustic dual-stream quantization. By disentangling semantic and acoustic modeling into two dedicated streams, SAC enables each to be optimized for its respective role. Comprehensive evaluations show that SAC achieves strong reconstruction performance across diverse bitrates under both clean and noisy conditions, with particularly high scores on UTMOS and WER, indicating superior naturalness and intelligibility. Moreover, SAC substantially surpasses prior codecs in semantic representation, approaching the level of continuous self-supervised embeddings. When used as a tokenizer for LLM-based text-to-speech, SAC enables a single-stage autoregressive (AR) TTS model that clearly outperforms state-of-the-art AR systems. Our disentanglement analysis further validates the effectiveness of the dual-stream design, offering new potential for controllable speech generation.

Donald Shenaj, Ondrej Bohdal, Taha Ceritli, Mete Ozay, Pietro Zanuttigh, Umberto Michieli

On-device deployment of Large Language Models (LLMs) frequently leverages Low-Rank Adapters (LoRAs) to support diverse downstream tasks under tight resource constraints. To address the limited storage capacity of mobile devices, recent works have explored model merging techniques to fuse multiple LoRAs into a single one. In practice, however, LoRAs are often delivered incrementally, as users request support for new tasks (e.g., novel problem types or languages). This scenario introduces a new challenge: on-device online continual merging, where the objective is to incorporate new LoRAs while preserving the performance on previously supported tasks. In this paper, we propose a data-free and computationally efficient strategy for selecting and merging LoRAs when a new one becomes available, assuming the device can store only a limited number of adapters. Extensive experiments across real-world tasks demonstrate the superiority of our approach compared to alternative strategies while adhering to the storage budget and compute limitations of on-device settings. The project page is available at: https://donaldssh.github.io/K-Merge.

Mingkuan Feng, Jinyang Wu, Siyuan Liu, Shuai Zhang, Hongjian Fang, Ruihan Jin, Feihu Che, Pengpeng Shao, Zhengqi Wen, Jianhua Tao

The deployment of large language models (LLMs) is largely hindered by their large number of parameters. Structural pruning has emerged as a promising solution. Prior structured pruning methods directly remove unimportant parameters based on certain metrics, which often causes knowledge loss and necessitates extensive retraining. To overcome this, we introduce a novel pruning method **TRSP**: **T**wo-Stage **R**egularization-Based **S**tructured **P**runing for LLMs. Specifically, we multiply the output of each transformer layer by an initial learnable weight and iteratively learn these weights by adding their \ell_1-norm as a regularization term to the loss function, serving as the first-stage regularization. Subsequently, we apply additional regularization to the difference between the output and input of layers with smaller weights, encouraging the shift of knowledge to the preserved layers. This serves as the second-stage regularization. TRSP retains more knowledge and better preserves model performance than direct parameter elimination. Through extensive experimentation we show that TRSP outperforms strong layer-wise structured pruning methods without requiring retraining. As a layer-wise pruning method, it delivers notable end-to-end acceleration, making it a promising solution for efficient LLM deployment.

Jinyang Wu, Mingkuan Feng, Shuai Zhang, Feihu Che, Zhengqi Wen, Chonghua Liao, Ling Yang, Haoran Luo, Zheng Lian, Jianhua Tao

In-context learning (ICL) leverages demonstrations to enhance the performance of large language models (LLMs). However, traditional ICL struggles with complex reasoning mainly due to superficial, example-level implicit imitation. To address these limitations, we introduce **ThoughtICR**, an automated **Thought**-level **I**n-**C**ontext **R**easoning paradigm that shifts from surface-level examples to more guidance-oriented thought patterns. Specifically, we first define atomic reasoning actions and construct thought patterns on small-scale seed data using Monte Carlo Tree Search (MCTS). During inference, we dynamically select appropriate thought patterns based on target problem attributes, providing explicit guidance for model reasoning. Thanks to its automated and strategic design, our method enables seamless plug-and-play integration with various post-training techniques. Experimental results demonstrate that our method improves performance across different model sizes and generalizes effectively across reasoning domains. Using only small-scale seed data, we achieve 80.6% accuracy on MATH and 62.5% on AMC, surpassing GPT-4o’s 77.2% and 57.5%, respectively. Moreover, compared to test-time scaling methods, our approach reduces computational costs by over 10. Our code is available at https://github.com/jinyangwu/ThoughtICR.

Xinyu Tang, Yuliang Zhan, Zhixun Li, Xin Zhao, Zhenduo Zhang, Zujie Wen, Zhiqiang Zhang, Jun Zhou

Large reasoning models (LRMs) are typically trained using reinforcement learning with verifiable reward (RLVR) to enhance their reasoning abilities. In this paradigm, policies are updated using both positive and negative self-generated rollouts, which correspond to distinct ***sample polarities***. In this paper, we provide a systematic investigation into how these sample polarities affect RLVR training dynamics and behaviors. We find that positive samples sharpen existing correct reasoning patterns, while negative samples encourage exploration of new reasoning paths. We further explore how adjusting the advantage values of positive and negative samples at both the polarity level and the token level affects RLVR training. Based on these insights, we propose an **A**daptive and **A**symmetric token-level **A**dvantage shaping method for **P**olicy **O**ptimization, namely **A3PO**, that more precisely allocates advantage signals to key tokens across different polarities. Experiments across five reasoning benchmarks demonstrate the effectiveness of our approach.