Singapore

Our statistical analysis reveals a complementary phenomenon between large language model-based question answering (QA) and small model-based QA. To facilitate dual knowledge transfer between these two paradigms, this paper introduces a collaborative enhancement method of large and small models for question answering. The proposed method consists of two iterative steps: i) small4large step, in which the small model first predicts an answer for a given question along with its confidence, and these results are then leveraged as prompts to strengthen the large model&#39;s performance; ii) large4small step, where the large model enhances the small model through distillation, judgment and reflection. Through iteration of these two steps, the large and small models could enhance each other progressively. Experimental evaluations across eight datasets spanning five domains demonstrate that the proposed method effectively improves the question answering performance of both large and small models simultaneously.

AAAI 2026

Collaborative Enhancement of Large and Small Models for Question Answering via Dual Knowledge Transfer

large language model

knowledge transfer

question answering

### Welcome to The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025)

Message from the General Chair: 
*It is my great pleasure and honor to welcome you to the 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025), held in beautiful Vienna, Austria, from July 27 to August 1, 2025. ACL2025continues our field’s tradition of excellence in scholarship, innovation, and inclusivity, and I am deeply grateful to the many volunteers who have worked tirelessly to bring this event to life.* 
[Read more](https://drive.google.com/file/d/1GI_hvOpjswAuYdUTromfeDiPpCcqidwg/view?usp=sharing)

To access this event page, you need to log in with the **email address you registered with**. Access credentials will be sent to your email from Underline - subject line "Welcome to ACL 2025". Please be sure to check your spam email folder if you do not see an email confirmation right away.

Please log in

To access this event page, you need to log in with the **email address you registered with**. 

ACL 2025

Welcome to The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025)

Our statistical analysis reveals a complementary phenomenon between large language model-based question answering (QA) and small model-based QA. To facilitate dual knowledge transfer between these two paradigms, this paper introduces a collaborative enhancement method of large and small models for question answering. The proposed method consists of two iterative steps: i) small4large step, in which the small model first predicts an answer for a given question along with its confidence, and these results are then leveraged as prompts to strengthen the large model's performance; ii) large4small step, where the large model enhances the small model through distillation, judgment and reflection. Through iteration of these two steps, the large and small models could enhance each other progressively. Experimental evaluations across eight datasets spanning five domains demonstrate that the proposed method effectively improves the question answering performance of both large and small models simultaneously.

technical paper

We are pleased to announce the Fortieth AAAI Conference on Artificial Intelligence (AAAI-26), which will be held in Singapore EXPO from January 20 to January 27, 2026.

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. AAAI-26 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and a range of other activities to be announced.

To access this event page, you need to log in with the **email address you registered with**. Access credentials will be sent to your email from Underline - subject line "Welcome to AAAI 2026". Please be sure to check your spam email folder if you do not see an email confirmation right away.

To access this event page, you are required to register.
Please complete your registration to continue.

We recommend reading [**the registration information**](https://aaai.org/conference/aaai/aaai-26/registration/) first.

**Online Registration Form**: https://aaai.getregistered.net/conference-2026 

Registration Required

We are pleased to announce the Fortieth AAAI Conference on Artificial Intelligence (AAAI-26), which will be held in Singapore EXPO from January 20 to January 27, 2026.

Current Multimodal Chain-of-Thought (MCoT) methods suffer from *low-quality multimodal reasoning*, characterized by overthinking on simple queries and inefficient utilization of visual information, resulting in vast inefficient and ineffective computations.
In this paper, we discover that Multimodal Large Language Models (MLLMs) possess inherent capabilities to distinguish between simple and difficult queries and enhance task-related visual information, which remain underutilized by existing approaches. 
Based on this insight, we propose Self-Driven Refined Multimodal CoT (SDR-MCoT), a training-free framework that mitigates these issues through two self-driven modules. 
First, our selective thinking module employs entropy-based confidence estimation to determine whether queries require detailed reasoning, preventing overthinking on simple questions. 
Second, our step-wise visual enhancement module strengthens attention to relevant visual regions at each reasoning step without inserting additional tokens, achieving fine-grained visual grounding and enhancement with minimal overhead. 
Moreover, SDR-MCoT can be seamlessly integrated into various MLLMs, offering a practical solution for improving multimodal reasoning.
Comprehensive experiments across eight benchmarks from diverse domains (multimodal reasoning, visual understanding, hallucination, and mathematical reasoning) demonstrate that SDR-MCoT consistently outperforms existing MCoT methods on four different base models with reduced overhead. 
For instance, on Qwen2-VL-7B, our method improves average accuracy by over 6\% while reducing token consumption by approximately 60\% compared to zero-shot CoT.

Mitigating Low-Quality Reasoning in MLLMs: Self-Driven Refined Multimodal CoT with Selective Thinking and Step-wise Visual Enhancement

The rapid proliferation of social media platforms has led to a surge in multimodal fake news, where deceptive content often combines text and images to mislead audiences. Traditional unimodal detection methods struggle to address the complexity of such content, necessitating holistic multimodal approaches. While the latest advancements in Multimodal Large Language Models (MLLMs) offer new opportunities for enhancing detection performance by analyzing multi-dimensional features, including source credibility, cross-modal contradictions, emotional bias, and manipulative writing patterns, these methods suffer from a key flaw: a susceptibility to hallucinations or erroneous reasoning, which can lead to flawed conclusions and ultimately biased detection results. We propose the Multimodal Fake News Detection via Multi-perspective Rationale Generation and Verification (MMRGV) model to mitigate this challenge. Our method employs a cross-verification mechanism to screen and reconcile contradictions among different rationales, thereby preserving the LLM's analytical advantages while mitigating the impact of erroneous reasoning or hallucinations on the final detection. Subsequently, these optimized rationales are fused via an adaptive weighting strategy to output a robust final prediction. Extensive experiments on three benchmark datasets (Twitter, Weibo, and GossipCop) demonstrate the superiority of our method, achieving state-of-the-art accuracy of 0.9972, 0.9663, and 0.8772, respectively, and significantly outperforming existing baselines. These results validate the effectiveness of multi-perspective rationale generation and cross-verification in enhancing multimodal fake news detection, offering a resilient solution to combat misinformation in the era of generative AI.

Toward Multimodal Fake News Detection by Multi-perspective Rationale Generation and Verification

In this paper, we study the data complexity of querying inconsistent weighted description logic (DL) knowledge bases under recently-introduced cost-based semantics. In a nutshell, the idea is to assign each interpretation a cost based upon the weights of the violated axioms and assertions, and certain and possible query answers are determined by considering all (resp. some) interpretations having optimal or bounded cost. Whereas the initial study of cost-based semantics focused on DLs between EL_bot and ALCO, we consider DLs that may contain inverse roles and role inclusions, thus covering prominent DL-Lite dialects. Our data complexity analysis goes significantly beyond existing results by sharpening several lower bounds and pinpointing the precise complexity of optimal-cost certain answer semantics (no non-trivial upper bound was known). Moreover, while all existing results show the intractability of cost-based semantics, our most challenging and surprising result establishes that if we consider DL-Lite^H_bool ontologies and a fixed cost bound, certain answers for instance queries and possible answers for conjunctive queries can be computed using first-order rewriting and thus enjoy the lowest possible data complexity (AC0).

Data Complexity of Querying Description Logic Knowledge Bases Under Cost-Based Semantics

We extend the seminal model of Pathak and Sönmez (2008) to a setting with multiple school districts, each running its own separate centralized match, and focus on the case of two districts. In our setting, in addition to each student being either sincere or sophisticated, she is also either constrained—able to apply only to schools within her own district of residence—or unconstrained—able to choose any single district within which to apply. We show that several key results from Pathak and Sönmez (2008) qualitatively flip: A sophisticated student may prefer for a sincere student to become sophisticated, and a sophisticated student may prefer for her own district to use Deferred Acceptance over the Boston Mechanism, irrespective of the mechanism used by the other district. We furthermore show that an unconstrained student may prefer for a constrained student to become unconstrained, regardless of the mechanisms used. Many of these phenomena appear abundantly in large random markets.

Multi-District School Choice: Playing on Several Fields

Existing feature engineering methods based on large language models (LLMs) have not yet been applied to multi-label learning tasks. They lack the ability to model complex label dependencies and are not specifically adapted to the characteristics of multi-label tasks. To address the above issues, we propose Feature Engineering Automation for Multi-Label Learning (FEAML), an automated feature engineering method for multi-label classification which leverages the code generation capabilities of LLMs. By utilizing metadata and label co-occurrence matrices, LLMs are guided to understand the relationships between data features and task objectives, based on which high-quality features are generated.The newly generated features are evaluated in terms of model accuracy to assess their effectiveness, while Pearson correlation coefficients are used to detect redundancy. FEAML further incorporates the evaluation results as feedback to drive LLMs to continuously optimize code generation in subsequent iterations. By integrating LLMs with a feedback mechanism, FEAML realizes an efficient, interpretable and self-improving feature engineering paradigm. Empirical results on various multi-label datasets demonstrate that our FEAML outperforms other feature engineering methods.

The Semantic Architect: How FEAML Bridges Structured Data and LLMs for Multi-Label Tasks

Large Language Models (LLMs) demonstrate impressive performance across natural language tasks but incur substantial computational and storage costs due to their scale. Post-training structured pruning offers an efficient solution. However, when few-shot calibration sets fail to adequately reflect the pretraining data distribution, existing methods exhibit limited generalization to downstream tasks. To address this issue, we propose Function-Aware Neuron Grouping (FANG), a post-training pruning framework that alleviates calibration bias by identifying and preserving neurons critical to specific function. FANG groups neurons with similar function based on the type of semantic context they process and prunes each group independently. During importance estimation within each group, tokens that strongly correlate with the functional role of the neuron group are given higher weighting. Additionally, FANG also preserves neurons that contribute across multiple context types. To achieve a better trade-off between sparsity and performance, it allocates sparsity to each block adaptively based on its functional complexity. Experiments show that FANG improves downstream accuracy while preserving language modeling performance. It achieves the state-of-the-art (SOTA) results when combined with FLAP and OBC, two representative pruning methods. Specifically, FANG outperforms FLAP and OBC by 1.5%–8.5% in average accuracy under 30% and 40% sparsity.

Improving Generalization in LLM Structured Pruning via Function-Aware Neuron Grouping

Discovering subgroups with the maximum average treatment effect is crucial for targeted decision making in domains such as precision medicine, public policy, and education. While most prior work is formulated in the potential‑outcome framework, the corresponding structural causal model (SCM) for this task has been largely overlooked. In practice, two approaches dominate. The first estimates pointwise conditional treatment effects and then fits a tree on those estimates, effectively turning subgroup estimation into the harder problem of accurate pointwise estimation. The second constructs decision trees or rule sets with ad‑hoc 'causal' heuristics, typically without rigorous justification for why a given heuristic may be used or whether such heuristics are necessary at all.

We address these issues by studying the problem directly under the SCM framework. Under the assumption of a partition-based model, we show that optimal subgroup discovery reduces to recovering the data-generating models and hence a standard supervised learning problem (regression or classification). This allows us to adopt \emph{any} partition-based methods to learn the subgroup from data. We instantiate the approach with CART, arguably one of the most widely used tree-based method, to learn the subgroup with maximum treatment effect. Finally, on a large collection of synthetic and semi‑synthetic datasets, we compare our method against a wide range of baselines and find that our approach, which avoids such causal heuristics, more accurately identifies subgroups with maximum treatment effect.

Learning Subgroups with Maximum Treatment Effects Without Causal Heuristics

Efficient inference of large language models (LLMs) is hindered by an ever-growing key-value (KV) cache, making KV cache compression a critical research direction. Traditional methods selectively evict less important KV cache entries, which leads to information loss and hallucinations. Recently, merging-based strategies have been explored to retain more information by merging KV pairs that would be discarded; however, these existing approaches inevitably introduce inconsistencies in attention distributions before and after merging, causing output perturbation and degraded generation quality. To overcome this challenge, we propose KeepKV, a novel adaptive KV cache merging method designed to preserve performance under strict memory constraints, taking a significant step toward achieving lossless KV cache compression. KeepKV introduces the Electoral Votes mechanism that records merging history and adaptively adjusts attention scores. Moreover, it further leverages a novel Zero Inference-Perturbation Merging method, compensating for attention loss resulting from cache merging. Extensive experiments on various benchmarks and LLM architectures demonstrate that KeepKV substantially reduces memory usage while successfully retaining essential context information, achieving over $2\times$ inference throughput improvement and maintaining superior generation quality even with only 10% KV cache budgets.

KeepKV: Achieving Periodic Lossless KV Cache Compression for Efficient LLM Inference

Robots have surpassed humans in terms of strength and
precision, yet humans retain an unparalleled ability for
decision-making in the face of unpredictable disturbances.
This article aims to combine the strengths of both entities
within a singular task: human motion guidance under strict
geometric constraints, particularly adhering to
predetermined paths. To tackle this challenge, a modular
haptic guidance law is proposed that takes the
human-applied wrench as an input. Using an auxiliary
variable called phase, the generated desired motion is
guaranteed to consistently adhere to the constraint path.
It is demonstrated how the guidance policy can be
generalized into physically interpretable terms, adjustable
either prior to initiating the task or dynamically while
the task is in progress. Additionally, an illustrative
guidance adaptation policy is showcased that takes into
account the human’s manipulability. Leveraging passivity
analysis, potential sources of instability are pinpointed,
and subsequently, overall system stability is ensured by
incorporating an augmented virtual energy tank. Lastly, a
comprehensive set of experiments, including a
20-participant user study, explores various aspects of the
approach in practice, encompassing both technical and
usability considerations.

Downloads

Next from AAAI 2026

Mitigating Low-Quality Reasoning in MLLMs: Self-Driven Refined Multimodal CoT with Selective Thinking and Step-wise Visual Enhancement

Similar lecture

The Role of Exploration Modules in Small Language Models for Knowledge Graph Question Answering

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from AAAI 2026

Mitigating Low-Quality Reasoning in MLLMs: Self-Driven Refined Multimodal CoT with Selective Thinking and Step-wise Visual Enhancement

Similar lecture

The Role of Exploration Modules in Small Language Models for Knowledge Graph Question Answering

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Downloads