Text-to-SQL aims to bridge the gap between human intent and relational databases. While LLMs have shown proficiency in generating simple SQL queries, they struggle with complex analytical tasks. Moreover, models fine-tuned on SQL generation often suffer from catastrophic forgetting, which lose the versatility of procedural reasoning and pertaining to generation constraints. Inspired by the usage of high-resource programming languages as LLM reasoning intermediaries, we propose CORES model, which leverages Python as a procedural reasoning pivot to enhance both complex SQL generation and tabular reasoning. It decomposes complex queries into Python reasoning traces before generating the final SQL, which bridges the gap between procedural reasoning and declarative expression. In order to internalize this reasoning capability, we fine-tune LLMs via GRPO with tailored process reward functions that mitigate the sparse feedback problem. We experimentally verify the effectiveness of CORES on six text-to-SQL benchmarks, where ours outperforms baselines by 6.44% on average, while maintains good capability on three tableQA benchmarks.
论文检索
输入标题、作者或关键词，从 100,903 篇学术成果中精准定位
Beyond Marginal Distributions: A Framework to Evaluate the Representativeness of Demographic-Aligned LLMs
PDF ↗Large language models are increasingly used to represent human opinions, values, or beliefs, and their steerability towards these ideals is an active area of research. Existing work focuses predominantly on aligning marginal response distributions, treating each alignment evaluation example independently. While essential, this may overlook deeper latent structures that characterise real populations and underpin cultural values theories. We propose a framework for evaluating the representativeness of aligned models through multivariate correlation patterns in addition to marginal distributions. We show the value of our evaluation scheme by comparing two model steering techniques (persona prompting and demographic fine-tuning) and evaluating them against human responses from the World Values Survey. While the demographic fine-tuned model better approximates marginal response distributions, persona prompting performs marginally better at reproducing the empirical correlation structure between survey items. Despite this reversal, neither technique aligns with human correlation patterns. We conclude that representativeness is a distinct aspect of value alignment and an evaluation focused on marginals can mask structural failures, leading to overly optimistic conclusions about model representativeness.
Autoregressive (AR) large audio language models (LALMs) such as Qwen-2.5-Omni have achieved strong performance on audio understanding and interaction, but scaling them remains costly in data and computation, and strictly sequential decoding limits inference efficiency. Diffusion large language models (dLLMs) have recently been shown to make effective use of limited training data, and prior work on DIFFA indicates that replacing an AR backbone with a diffusion counterpart can substantially improve audio understanding under matched settings, albeit at a proof-of-concept scale without large-scale instruction tuning, preference alignment, or practical decoding schemes. We introduce DIFFA-2, a practical diffusion-based LALM for general audio understanding. DIFFA-2 upgrades the speech encoder, employs dual semantic and acoustic adapters, and is trained with a four-stage curriculum that combines semantic and acoustic alignment, large-scale supervised fine-tuning, and variance-reduced preference optimization, using only fully open-source corpora. Experiments on MMSU, MMAU, and MMAR show that DIFFA-2 consistently improves over DIFFA and is competitive to strong AR LALMs under practical training budgets, supporting diffusion-based modeling is a viable backbone for large-scale audio understanding.
Once Correct, Still Wrong: Counterfactual Hallucination in Multilingual Vision-Language Models
PDF ↗Vision–language models (VLMs) can achieve high accuracy while still accepting **culturally plausible but visually incorrect** interpretations. Existing hallucination benchmarks rarely test this failure mode, particularly outside Western contexts and English. We introduce **M^2CQA**, a culturally grounded multimodal benchmark built from images spanning 17 MENA countries, paired with contrastive true and counterfactual statements in English, Arabic, and its dialects. To isolate hallucination beyond raw accuracy, we propose the **CounterFactual Hallucination Rate (CFHR)**, which measures counterfactual acceptance conditioned on correctly answering the true statement. Evaluating state-of-the-art VLMs under multiple prompting strategies, we find that CFHR rises sharply in Arabic, especially in dialects, even when true-statement accuracy remains high.Moreover, reasoning-first prompting consistently increases counterfactual hallucination, while answering before justifying improves robustness. We make the dataset publicly available for the community (https://huggingface.co/datasets/QCRI/M2CQA)).
MAC-Reasoner: A Multi-Agent Collaborative Framework for Enhancing Logical Reasoning in Large Language Models
PDF ↗Large language models (LLMs) face challenges in logical reasoning where correctness requires strict deductive procedures. Purely model-based approaches often suffer from hallucinations, while neuro-symbolic methods typically delegate deduction to external solvers, reducing the LLM to a mere translator. To address this, we propose MAC-Reasoner, a multi-agent framework that constructs a Logic-Augmented Context to enhance LLMs’ reasoning. In this framework, a translator agent converts problems into executable symbolic programs. Symbolic information from solver execution is transformed into the Logic-Augmented Context, serving as a verification reference where logical conflicts trigger heightened attention to violated constraints. We evaluate MAC-Reasoner with three backbone LLMs on four challenging benchmarks. Results show consistent and robust improvements over baselines. Furthermore, reasoning traces from MAC-Reasoner can be used for supervised fine-tuning of LLMs to achieve more accurate and efficient logical reasoning.
Goal-directed molecular generation requires satisfying heterogeneous constraints such as protein–ligand compatibility and multi-objective drug-like properties, yet existing methods often optimize these constraints in isolation, failing to reconcile conflicting objectives (e.g., affinity vs. safety), and struggle to navigate the non-differentiable chemical space without compromising structural validity. To address these challenges, we propose CAGenMol, a condition-aware discrete diffusion framework over molecular sequences that formulates molecular design as conditional denoising guided by heterogeneous structural and property signals. By coupling discrete diffusion with reinforcement learning, the model aligns the generation trajectory with non-differentiable objectives while preserving chemical validity and diversity. The non-autoregressive nature of diffusion language model further enables iterative refinement of molecular fragments at inference time. Experiments on structure-conditioned, property-conditioned, and dual-conditioned benchmarks demonstrate consistent improvements over state-of-the-art methods in binding affinity, drug-likeness, and success rate, highlighting the effectiveness of our framework. The code is available at https://github.com/Lee612-1/CAGenMol.
Recently, large language models (LLMs) have demonstrated impressive performance but still suffer from hallucinations. Model editing has been proposed as a means to correct factual inaccuracies. A challenging scenario is sequential model editing (SME), which aims to rectify errors continuously, rather than a one-time task. During SME, the general capabilities of LLMs can be negatively affected due to the introduction of new parameters. In this paper, we propose a queue-based self-correction framework, QueueEDIT, that not only enhances SME performance by addressing long-sequence dependencies but also mitigates the impact of parameter bias on the general capabilities of LLMs. Specifically, we first introduce a structural mapping editing loss to map editing triplets to knowledge-sensitive neurons within the Transformer layers. We then store the located parameters for each piece of edited knowledge in a queue and dynamically align previously edited parameters. At each edit, we select parameters in the queue that are most relevant to currently located parameters to determine whether knowledge associated with previous edits requires realignment. Irrelevant parameters in the queue are frozen, and we update the parameters at the queue head into the LLM to ensure they do not harm general capabilities. Experiments show that QueueEDIT significantly outperforms strong baselines across various SME settings, while maintaining competitive performance in single-turn editing. Resulting LLMs also preserve high performance on general NLP tasks throughout the SME process.
The stateless architecture of Large Language Models inherently lacks the mechanism to preserve dynamic context, compelling agents to redundantly reprocess history to maintain long-horizon autonomy. While latent memory offers a solution, current approaches are hindered by architectural segregation, relying on auxiliary encoders that decouple memory from the reasoning backbone. We propose FlashMem, a framework that distills intrinsic memory directly from transient reasoning states via computation reuse. Leveraging the property that internal representations uniquely encode input trajectories, FlashMem identifies the last hidden state as a sufficient statistic for the interaction history. This enables a Shared-KV Consolidator to synthesize memory by attending directly to the backbone’s frozen cache, eliminating redundant re-parameterization. Furthermore, a parameter-free Cognitive Monitor leverages attention entropy to adaptively trigger consolidation only when high epistemic uncertainty is detected. Experiments demonstrate that FlashMem matches the performance of heavy baselines while reducing inference latency by 5 times, effectively bridging the gap between efficiency and persistent cognition.
Reason in Chains, Learn in Trees: Self-Rectification and Grafting for Multi-turn Agent Policy Optimization
PDF ↗Reinforcement learning for Large Language Model agents is often hindered by sparse rewards in multi-step reasoning tasks. Existing approaches like Group Relative Policy Optimization treat sampled trajectories as independent chains, assigning uniform credit to all steps in each chain and ignoring the existence of critical steps that may disproportionally impact reasoning outcome. In this paper, we propose T-STAR(Tree-structured Self-Taught Agent Rectification), a framework that recovers the latent correlated reward structure across seemingly independent trajectories. Specifically, we consolidate trajectories into a unified Cognitive Tree by identifying and merging functionally similar steps/nodes. It enables an Introspective Valuation mechanism that back-propagates trajectory-level rewards through the tree to obtain a new notion of variance-reduced relative advantage at step-level. Using the Cognitive Tree, we also develop In-Context Thought Grafting to synthesize corrective reasoning by contrasting successful and failed branches at critical divergence points/steps. Our proposed Surgical Policy Optimization then capitalizes on the rich policy gradient information concentrated at these critical points/steps through a Bradley-Terry type of surgical loss. Extensive experiments across embodied, interactive, reasoning, and planning benchmarks demonstrate that T-STAR achieves consistent improvements over strong baselines, with gains most pronounced on tasks requiring extended reasoning chains.
Chain-of-Thought (CoT) prompting improves reasoning but often produces long and redundant traces that substantially increase inference cost. We present SyncThink, a training-free and plug-and-play decoding method that reduces CoT overhead without modifying model weights. We find that answer tokens attend weakly to early reasoning and focus on ‘</think>‘, indicating an information bottleneck.Building on this observation, SyncThink monitors the model’s own reasoning-transition signal and terminates reasoning. Experiments on GSM8K, MMLU, GPQA, and BBH across three DeepSeek-R1 distilled models show that SyncThink achieves 62.00% average Top@1 accuracy using 656 generated tokens and 28.68s latency, compared to 61.22%, 2141 tokens, and 92.01s for full CoT decoding. On long-horizon tasks such as GPQA, SyncThink can further yield up to +8.1 absolute accuracy by preventing over-thinking.
ReCoT-NER: Enhancing Zero-Shot Named Entity Recognition through Chain-of-Thought Prompting and Recall-Oriented Loss Optimization
PDF ↗Named Entity Recognition (NER) plays a fundamental role in information extraction and domain knowledge construction. However, in specialized domains such as wind power fault diagnosis, the scarcity of labeled data makes supervised approaches impractical. Zero-shot NER provides a promising alternative but still struggles with incomplete entity detection and unstable generation boundaries. To address these challenges, we propose ReCoT-NER, a reasoning-enhanced generative framework that integrates Chain-of-Thought (CoT) prompting and recall-oriented loss optimization. The proposed CoT instruction design explicitly decomposes NER into two reasoning stages: entity span detection and entity type classification. This enables the model to follow a structured inference process. In addition, we introduce a recall-oriented loss function that reweights entity and non-entity tokens to mitigate false negatives, encouraging more inclusive entity coverage. Experiments on CrossNER, MIT, and a newly constructed wind-power NER dataset demonstrate that ReCoT-NER consistently improves recall and overall F1 performance across both general and industrial domains. Notably, ReCoT-NER achieves competitive results with just a 77M-parameter model, making it well-suited for low-resource zero-shot settings. The code for our method is publicly available at https://github.com/10637409100/RECOTNER.
Recent work on domain-specific reasoning with large language models (LLMs) has largely relied on training-intensive approaches that require updating model parameters. Although activation steering has emerged as a parameter-efficient alternative, existing methods typically rely on static and manually designed interventions, limiting their ability to adapt to the dynamic nature of complex reasoning. To address this limitation, we propose RISER (Router-based Intervention for Steerable Enhancement of Reasoning), a plug-and-play intervention framework that adaptively steers LLM reasoning in activation space. RISER builds a library of reusable reasoning vectors and employs a lightweight Router to dynamically compose these vectors for each input. The Router is optimized via reinforcement learning under task-level rewards, enabling the emergent and compositional activation of latent cognitive primitives. Across seven diverse benchmarks, RISER achieves average zero-shot accuracy improvements of 3.4–6.5% over the base model, while outperforming chain-of-thought-style reasoning with 2–3× higher token efficiency and robust accuracy gains. Further analysis demonstrates that RISER autonomously combines multiple vectors into interpretable and precise control strategies, pointing toward more controllable and efficient LLM reasoning.
Large language models (LLMs) are known to exhibit gender bias, yet most evaluations focus on downstream stereotypes rather than the normative frameworks that shape model inference. We investigate whether LLMs rely on traditional masculinity norms (e.g. "real men are tough") as latent priors in gender-biased inference. We ground our evaluation in the Male Role Norms Inventory (MRNI), a validated psychological framework of prescriptive male role norms.Anchored in MRNI items, we probe models using two complementary approaches: (i) explicit Likert-style agreement with masculinity norms, and (ii) a newly crafted English-Italian scenario-based inference dataset (MRNI-BB), in which gender information and evidential support are systematically varied. Across models, explicit endorsement of masculinity norms is generally low. In contrast, in scenario-based inference tasks, models systematically attribute MRNI-aligned behaviors to male agents, even when evidence is ambiguous or absent. This effect disappears when gender markers are removed, suggesting that masculinity norms are treated as gender-specific expectations about male agents. Increasing model scale reduces explicit norm endorsement but is associated with stronger male-directed bias under uncertainty.
Heterogeneity in Formal Linguistic Competence of Language Models: Is Data the Real Bottleneck?
PDF ↗Large Language Models (LLMs) exhibit a puzzling disparity in their formal linguistic competence: while they learn some linguistic phenomena with near-perfect mastery, they often perform below chance on others, even after training on trillions of tokens. In this work, we investigate whether these failures stem from inherent architectural limitations or simply the scarcity of these specific grammatical constructions in web-scale corpora. We pre-train simple GPT-2 Small (124M) models on a 100M-token random sample of the FineWeb corpus and intervene by injecting a minimal amount (1%) of synthetic data targeting specific linguistic phenomena. We find that this targeted intervention substantially improves model performance in 8 out of the 9 worst-performing BLiMP paradigms – notably the accuracy on a specific paradigm, only_npi_scope, surges from 20.9% to 69.4%. Furthermore, we observe that these interventions generally preserve or slightly improve aggregate performance. However, while we also identify a resistant phenomenon, principle_A_c_command, whose performance remains below chance even after our data augmentation, our findings do serve as an optimistic existence proof that even small language models can substantially improve on those linguistic phenomena on which models typically perform poorly, provided the pre-training data contains sufficient exposure to them. This suggests that efforts towards human-scale language modeling may benefit greatly by focusing on data composition. The code to reproduce our results is open-sourced at https://github.com/kowndinya-renduchintala/heterogeneity-in-formal-linguistic-competence.
TinyAlign: Boosting Lightweight Vision-Language Models by Mitigating Modal Alignment Bottlenecks
PDF ↗Lightweight Vision-Language Models (VLMs) are indispensable for resource-constrained applications. The prevailing approach to aligning vision and language models involves freezing both the vision encoder and the language model while training small connector modules. However, this strategy heavily depends on the intrinsic capabilities of the language model, which can be suboptimal for lightweight models with limited representational capacity. In this work, we investigate this alignment bottleneck through the lens of mutual information, positing that the constrained capacity of the language model inherently limits the Effective Mutual Information (EMI) between multimodal inputs and outputs, thereby compromising alignment quality. To address this challenge, we propose TinyAlign, a novel framework inspired by Retrieval-Augmented Generation, which strategically retrieves relevant context from a memory bank constructed from training data to enrich multimodal inputs and enhance their alignment. Extensive empirical evaluations reveal that TinyAlign significantly reduces training loss, accelerates convergence, and enhances task performance with negligible computational overhead. Remarkably, it allows models to achieve baseline-level performance with only 40% of the fine-tuning data, highlighting exceptional data efficiency. Our work thus offers a practical pathway for developing more capable lightweight VLMs while introducing a fresh theoretical lens to better understand and address alignment bottlenecks in constrained multimodal systems.
The Double Bind: Revisiting Preprinting and Peer Review Two Years After the Removal of the ACL Anonymity Period
PDF ↗ACL removed the anonymity period for conference submissions in February 2024, allowing unrestricted preprinting during review.To examine how preprints and author recognition affect outcomes across institutional hierarchies, we track preprinting trends for 47k publications, survey 75 NLP researchers, interview 14 community members, and analyze 1.9k peer reviews. We observe that more elite institutions post preprints more frequently (52% vs. 36% by 2025). Most participants agree that preprinting gives these institutions an advantage in peer review, and indeed, reviewer knowledge of authors inflates scores at elite institutions (d = 0.43, p < 0.001) but not elsewhere, also lowering review quality. Nonetheless, the anonymity period was found largely ineffective; instead, underrepresented researchers emphasize struggles with visibility, review quality, and external structural barriers. To counteract these inequities, we make recommendations for review quality improvement and increasing investment in diversity initiatives that center the perspectives of affected communities.
Opinion summarization systems aggregate customer sentiments without capturing the emotional factors that drive purchasing decisions, resulting in shallow summaries that overlook the affective dimensions shaping customer experiences and fail to explain why customers feel the way they do. This gap exists because prior research has neglected the interplay between expressed opinions and their underlying emotional contexts. To bridge this gap, we introduce Emotion-Aware Opinion Summarization (EAOS), a framework leveraging Large Language Models (LLMs) to integrate emotional dimensions into opinion summaries, moving beyond conventional sentiment polarity. To support this task, we develop a large-scale (40K product–summary pairs) training dataset, an evaluation benchmark, a compact 1B-parameter model that matches 70B-scale performance via knowledge distillation, and methods for generating and evaluating emotion-aware summaries. A user study shows that 82% of readers prefer our emotion-aware summaries (p < .001), confirming that adding emotion helps in making purchase decisions.
Large language models (LLMs) for code generation have achieved remarkable progress in synthesizing functional code from natural language instructions. However, a critical challenge persists in generating visually accurate and structurally sound front-end code that faithfully renders user-intended layouts and interfaces. Most existing works focus primarily on functional correctness, overlooking the visual fidelity and rendering quality essential for front-end development. To address this gap, we present a comprehensive data construction and training pipeline to enhance front-end code generation capabilities in code LLMs. We use a three-stage training approach: continual pre-training on synthetic data, quality-controlled supervised fine-tuning, and reinforcement learning with checklist-based rewards to improve model performance. Our comprehensive evaluation on front-end code generation benchmarks reveals that even strong base models struggle with visual faithfulness and layout complexity. Our fully-trained model demonstrated substantial improvements over baseline approaches across all domains, achieving competitive performance with frontier models while maintaining generation efficiency, underscoring the critical importance of stage-aligned data curation and vision-grounded optimization in developing reliable front-end code generation systems. Our code and data are open-sourced at https://github.com/leanfeng1/FrontCoder.
Post-training paradigms for Large Language Models (LLMs), primarily Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL), face a fundamental dilemma: SFT provides stability (low variance) but suffers from high fitting bias, while RL enables exploration (low bias) but grapples with high gradient variance. Existing unified optimization strategies often employ naive loss weighting, overlooking the statistical conflict between these distinct gradient signals. In this paper, we provide a rigorous theoretical analysis of this bias-variance trade-off and propose DYPO (Dynamic Policy Optimization), a unified framework designed to structurally mitigate this conflict. DYPO integrates three core components: (1) a Group Alignment Loss (GAL) that leverages intrinsic group dynamics to significantly reduce RL gradient variance; (2) a Multi-Teacher Distillation mechanism that corrects SFT fitting bias via diverse reasoning paths; and (3) a Dynamic Exploitation-Exploration Gating mechanism that adaptively arbitrates between stable SFT and exploratory RL based on reward feedback. Theoretical analysis confirms that DYPO linearly reduces fitting bias and minimizes overall variance. Extensive experiments demonstrate that DYPO significantly outperforms traditional sequential pipelines, achieving an average improvement of 4.8% on complex reasoning benchmarks and 13.3% on out-of-distribution tasks.
Finding RELIEF: Shaping Reasoning Behavior without Reasoning Supervision via Belief Engineering
PDF ↗Large reasoning models (LRMs) have achieved remarkable success through step-by-step chains of thought, yet they often suffer from excessive redundancy or unfaithful reasoning. Existing methods for shaping LRM behavior typically rely on reinforcement learning or fine-tuning with gold-standard reasoning traces, a paradigm that is both computationally expensive and difficult to scale. In this paper, we reveal that LRMs possess latent reasoning beliefs that internally track their own reasoning traits, which can be captured through simple logit probing without specialized training. Building on this insight, we propose Reasoning Belief Engineering (RELIEF), a simple yet effective framework that shapes LRM behavior by aligning the model’s self-concept with a target belief blueprint. Crucially, RELIEF completely bypasses the need for reasoning-trace supervision. It internalizes desired traits by fine-tuning on synthesized, self-reflective QA pairs that affirm the target belief. Extensive experiments on efficiency and faithfulness tasks demonstrate that RELIEF matches or outperforms behavior-supervised and preference-based baselines while requiring significantly lower training costs. Our analysis further validates that shifting a model’s reasoning belief effectively shapes its actual behavior.