Papers by Liangming Pan

Fact-Checking Complex Claims with Program-Guided Reasoning (2023.acl-long)

Challenge:	Existing agentic systems cannot search the whole design space due to the restriction of human-designed components.
Approach:	They propose a Gödel Agent framework that allows agents to recursively improve themselves without relying on fixed algorithms or fixed algorithms.
Outcome:	The proposed framework surpasses manual crafted agents in performance, efficiency, and generalizability.

Copied to clipboard

Liangming Pan, Xiaobao Wu, Xinyuan Lu, Anh Tuan Luu, William Yang Wang, Min-Yen Kan, Preslav Nakov

Programming Languages in NLP

Challenge:	Fact-checking real-world claims often requires collecting multiple pieces of evidence and complex multi-step reasoning.
Approach:	They propose a novel fact-checking model that decomposes complex claims into simpler sub-tasks that can be solved using a shared library of specialized functions.
Outcome:	The proposed model outperforms seven baselines on two fact-checking datasets and has explicit output programs that benefit human debugging.

Modeling Dynamic Topics in Chain-Free Fashion by Evolution-Tracking Contrastive Learning and Unassociated Word Exclusion (2024.findings-acl)

Copied to clipboard

Xiaobao Wu, Xinshuai Dong, Liangming Pan, Thong Nguyen, Anh Tuan Luu

Towards a Mechanistic Understanding of Large Reasoning Models: A Survey of Training, Inference, and Failures (2026.acl-long)

Challenge:	Existing dynamic topic models lack the ability to reveal the evolution of topics . Existing models suffer from repetitive topic and unassociated topic issues .
Approach:	They propose a new evolution-tracking contrastive learning method that builds the similarity relations among dynamic topics and an unassociated word exclusion method to avoid unassociated topics.
Outcome:	The proposed model outperforms state-of-the-art models on downstream tasks and is robust to evolution intensities.

Copied to clipboard

Yi Hu, Jiaqi Gu, Ruxin Wang, Zijun Yao, Hao Peng, Xiaobao Wu, Jianhui Chen, Muhan Zhang, Liangming Pan

KHANQ: A Dataset for Generating Deep Questions in Education (2022.coling-1)

Challenge:	Recent research has shown that reinforcement learning can elicit intriguing emergent reasoning behaviors.
Approach:	They propose a comprehensive survey of the mechanistic understanding of large reasoning models . they organize findings into three core dimensions: 1) training dynamics, 2) reasoning mechanisms, and 3) unintended behaviors.
Outcome:	This paper synthesizes the mechanistic understanding of large reasoning models into three dimensions . authors outline a roadmap for future studies including improved interpretability and methodologies .

Copied to clipboard

Huanli Gong, Liangming Pan, Hengchang Hu

Low-Resource NLP

Challenge:	Existing QG datasets are not suitable for educational question generation because the questions are not real questions asked by humans during learning.
Approach:	They propose a dataset for question generation that contains 1,034 high-quality learner-generated questions seeking an in-depth understanding of the taught online courses in Khan Academy.
Outcome:	The proposed dataset contains 1,034 high-quality learner-generated questions seeking an in-depth understanding of the taught online courses in Khan Academy.

QACheck: A Demonstration System for Question-Guided Multi-Hop Fact-Checking (2023.emnlp-demo)

Copied to clipboard

Liangming Pan, Xinyuan Lu, Min-Yen Kan, Preslav Nakov

Knowledge of Knowledge: Exploring Known-Unknowns Uncertainty with Large Language Models (2024.findings-acl)

Challenge:	Existing fact-checking systems lack transparency in their decision-making process, making it difficult for users to comprehend their reasoning process.
Approach:	They propose a Question-guided Multi-hop Fact-Checking system which asks a series of questions critical for verifying a claim.
Outcome:	The proposed model provides a comprehensive report detailing its reasoning process, guided by a sequence of questions, answer pairs, and the source of evidence supporting each question.

Copied to clipboard

Alfonso Amayuelas, Kyle Wong, Liangming Pan, Wenhu Chen, William Yang Wang

CausalEval: Towards Better Causal Reasoning in Language Models (2025.naacl-long)

Challenge:	Known-unknown questions are characterized by high uncertainty due to the absence of definitive answers.
Approach:	They introduce a dataset with known-unknown questions and establish a categorization framework to clarify the origins of uncertainty in such queries.
Outcome:	The proposed model improved in distinguishing between known and unknown queries within open-ended question-answering scenarios.

Copied to clipboard

Longxuan Yu, Delin Chen, Siheng Xiong, Qingyang Wu, Dawei Li, Zhikai Chen, Xiaoze Liu, Liangming Pan

Aristotle: Mastering Logical Reasoning with A Logic-Complete Decompose-Search-Resolve Framework (2025.acl-long)

Challenge:	Large language models (LLMs) have been used for a variety of tasks, including problem-solving, decision-making, and understanding of the world.
Approach:	They propose a review of existing methods aimed at enhancing LMs for causal reasoning . they categorize existing methods as reasoning engines or as helpers providing knowledge or data to traditional methods .
Outcome:	The proposed methods perform better than existing methods on a range of tasks.

Copied to clipboard

Jundong Xu, Hao Fei, Meng Luo, Qian Liu, Liangming Pan, William Yang Wang, Preslav Nakov, Mong-Li Lee, Wynne Hsu

Expertise Style Transfer: A New Task Towards Better Communication between Experts and Laymen (2020.acl-main)

Challenge:	Existing systems fail to fully leverage the structure of logical tasks throughout the reasoning process, causing bottlenecks in efficiency and efficacy.
Approach:	They propose a logic-complete reasoning framework, Aristotle, which integrates symbolic expressions and logical rules into the entire reasoning process.
Outcome:	The proposed framework outperforms state-of-the-art reasoning frameworks in accuracy and efficiency.

Copied to clipboard

Yixin Cao, Ruihao Shui, Liangming Pan, Min-Yen Kan, Zhiyuan Liu, Tat-Seng Chua

Text Generation

Challenge:	a curse of knowledge can impede communication between experts and laymen.
Approach:	They propose a task of expertise style transfer to automate the communication between experts and laymen using an annotated dataset.
Outcome:	The proposed task simplifies professional language and improves accuracy and expertise level of laymen descriptions using simple words.

Zero-shot Fact Verification by Claim Generation (2021.acl-short)

Copied to clipboard

Liangming Pan, Wenhu Chen, Wenhan Xiong, Min-Yen Kan, William Yang Wang

AntiLeakBench: Preventing Data Contamination by Automatically Constructing Benchmarks with Updated Real-World Knowledge (2025.acl-long)

Challenge:	Existing methods for fact verification require large datasets, which can be expensive.
Approach:	They propose a framework for training a robust fact verification model by using automatically generated claims that can be supported, refuted, or unverifiable from evidence from Wikipedia.
Outcome:	The proposed framework reduces the demand for human-annotated training data and improves a model's F1 from 50% to 77%, equivalent in performance to 2K+ manually-curated examples.

Copied to clipboard

Xiaobao Wu, Liangming Pan, Yuxi Xie, Ruiwen Zhou, Shuai Zhao, Yubo Ma, Mingzhe Du, Rui Mao, Anh Tuan Luu, William Yang Wang

InductionBench: LLMs Fail in the Simplest Complexity Class (2025.acl-long)

Challenge:	Existing studies solve this challenge by updating benchmarks with newly collected data, but they fail to guarantee contamination-free evaluation as the newly collected knowledge may contain pre-existing knowledge.
Approach:	They propose an automated anti-leakage benchmarking framework that builds and updates benchmarks without human labor instead of using newly collected data.
Outcome:	The proposed framework significantly reduces the cost of benchmark maintenance to accommodate emerging LLMs.

Copied to clipboard

Wenyue Hua, Tyler Wong, Fei Sun, Liangming Pan, Adam Jardine, William Yang Wang

On the Risk of Misinformation Pollution with Large Language Models (2023.findings-emnlp)

Challenge:	Existing benchmarks focus on deductive reasoning, largely overlooking inductive reasoning.
Approach:	They propose a benchmark to evaluate the inductive reasoning ability of large language models.
Outcome:	The proposed benchmark demonstrates that even the most advanced modelw struggle to master the simplest complexity classes within the subregular hierarchy of functions.

Copied to clipboard

Yikang Pan, Liangming Pan, Wenhu Chen, Preslav Nakov, Min-Yen Kan, William Wang

SeaKR: Self-aware Knowledge Retrieval for Adaptive Retrieval Augmented Generation (2025.acl-long)

Challenge:	a recent study demonstrates that large language models can be misused for generating credible-sounding misinformation . however, the ability to produce credible text raises concerns regarding their potential misuse .
Approach:	They propose three defense strategies to mitigate misinformation generated by Large Language Models . they propose a threat model and simulate potential misuse scenarios .
Outcome:	The proposed defense strategies have shown promising results, albeit with costs.

Copied to clipboard

Zijun Yao, Weijian Qi, Liangming Pan, Shulin Cao, Linmei Hu, Liu Weichuan, Lei Hou, Juanzi Li

Information Retrieval

Challenge:	Adaptive Retrieval-Augmented Generation (RAG) is an effective strategy to alleviate hallucination of large language models (LLMs).
Approach:	They propose a novel adaptive RAG model that extracts self-aware uncertainty of large language models from their internal states and invokes retrieval accordingly.
Outcome:	The proposed model outperforms existing adaptive RAG methods on complex and simple Question Answering datasets.

Unsupervised Multi-hop Question Answering by Question Generation (2021.naacl-main)

Copied to clipboard

Liangming Pan, Wenhu Chen, Wenhan Xiong, Min-Yen Kan, William Yang Wang

Low-Resource NLP

Challenge:	Existing training data for multi-hop question answering (QA) is time-consuming and resource-intensive.
Approach:	They propose an unsupervised framework that generates human-like multi-hop training data from homogeneous and heterogeneously data sources.
Outcome:	The proposed framework achieves 61% and 83% of the supervised learning performance for the HybridQA and HotpotQA datasets.

Factcheck-Bench: Fine-Grained Evaluation Benchmark for Automatic Fact-checkers (2024.findings-emnlp)

Copied to clipboard

Yuxia Wang, Revanth Gangi Reddy, Zain Mujahid, Arnav Arora, Aleksandr Rubashevskii, Jiahui Geng, Osama Mohammed Afzal, Liangming Pan, Nadav Borenstein, Aditya Pillai, Isabelle Augenstein, Iryna Gurevych, Preslav Nakov

INSTRUCTSCORE: Towards Explainable Text Generation Evaluation with Automatic Feedback (2023.emnlp-main)

Challenge:	Large language models generate naturally sounding answers over a broad range of human inquiries, but they often generate answers that contradict real-world facts.
Approach:	They propose a framework for annotating and evaluating the factuality of large language models . they propose 'factcheck-bench' which provides a multi-stage annotation scheme .
Outcome:	The proposed framework outperforms several popular LLM fact-checkers in claim, sentence, and document levels.

Copied to clipboard

Wenda Xu, Danqing Wang, Liangming Pan, Zhenqiao Song, Markus Freitag, William Wang, Lei Li

MultiAgent Collaboration Attack: Investigating Adversarial Attacks in Large Language Model Collaborations via Debate (2024.findings-emnlp)

Challenge:	Existing methods to evaluate the quality of language generation do not provide explicit explanation of their verdicts.
Approach:	They propose a fine-grained explainable evaluation metric for text generation that harnesses human instruction and implicit knowledge of GPT-4 to fine-tune it.
Outcome:	The proposed model outperforms all other unsupervised metrics on translation, captioning, data-to-text, and commonsense generation tasks.

Copied to clipboard

Alfonso Amayuelas, Xianjun Yang, Antonis Antoniades, Wenyue Hua, Liangming Pan, William Yang Wang

Exploring and Evaluating Attributes, Values, and Structures for Entity Alignment (2020.emnlp-main)

Challenge:	Large Language Models (LLMs) have shown exceptional results when working individually, and have reduced parameter size and inference times.
Approach:	They evaluate the behavior of a network of models collaborating through debate under the influence of an adversary and examine inference-time methods to generate more compelling arguments.
Outcome:	The proposed model-based model-driven analysis shows that the model-led model-mediated debates generate more compelling arguments and provide a defensive strategy.

Copied to clipboard

Zhiyuan Liu, Yixin Cao, Liangming Pan, Juanzi Li, Zhiyuan Liu, Tat-Seng Chua

Structured Data in NLP

Challenge:	Entity alignment (EA) aims at building a Knowledge Graph (KG) of rich content by linking the equivalent entities from various KGs.
Approach:	They propose to use an attributed value encoder to partition a Knowledge Graph into subgraphs to model the various types of attribute triples efficiently.
Outcome:	The proposed method achieves significant improvements over 12 baselines in cross-lingual and monolingual datasets.

Investigating the Transferability of Code Repair for Low-Resource Programming Languages (2025.findings-naacl)

Copied to clipboard

Kyle Wong, Alfonso Amayuelas, Liangming Pan, William Yang Wang

Interpreting the Robustness of Neural NLP Models to Textual Perturbations (2022.findings-acl)

Challenge:	Large language models (LLMs) have shown remarkable performance on code generation tasks.
Approach:	They investigate the benefits of distilling the ability to repair code for both high and low resource languages to determine if the techniques are also applicable in low resource settings.
Outcome:	The proposed techniques are effective in high- and low-resource languages, but weak in low-level languages.

Copied to clipboard

Yunxiang Zhang, Liangming Pan, Samson Tan, Min-Yen Kan

TART: An Open-Source Tool-Augmented Framework for Explainable Table-based Reasoning (2025.findings-naacl)

Challenge:	Modern Natural Language Processing models are sensitive to input perturbations and their performance can decrease when applied to noisy data.
Approach:	They propose to explain the extent to which a model is affected by an unseen textual perturbation by the learnability of the perturbation.
Outcome:	The proposed model is better at identifying a perturbation (higher learnability) but worse at ignoring it (lower robustness).

Copied to clipboard

Xinyuan Lu, Liangming Pan, Yubo Ma, Preslav Nakov, Min-Yen Kan

Towards Verifiable Generation: A Benchmark for Knowledge-aware Language Model Attribution (2024.findings-acl)

Challenge:	Current Large Language Models lack ability to understand table structures and apply precise numerical reasoning.
Approach:	They propose a tool-augmented reasoning framework for table-based tasks that integrates LLMs with specialized tools.
Outcome:	The proposed framework improves on the TOOLTAB dataset, a benchmark for LLMs in table–tool integration.

Copied to clipboard

Xinze Li, Yixin Cao, Liangming Pan, Yubo Ma, Aixin Sun

A Survey on Detection of LLMs-Generated Content (2024.findings-emnlp)

Challenge:	Existing evaluation metrics and benchmarks to attribute large language models to structured knowledge are lacking.
Approach:	They propose a task of Knowledge-aware Language Model Attribution that improves upon three core concerns with conventional attributed LMs.
Outcome:	The proposed model improves upon core concerns with conventional attributed LMs.

Copied to clipboard

Xianjun Yang, Liangming Pan, Xuandong Zhao, Haifeng Chen, Linda Petzold, William Yang Wang, Wei Cheng

Challenge:	Recent advances in large language models have led to an increase in synthetic content generation . the ability to detect LLMs-generated content has become of paramount importance .
Approach:	They propose to provide a detailed overview of existing detection strategies and benchmarks, scrutinizing their differences and advocating for more adaptable and robust models to enhance detection accuracy.
Outcome:	The proposed model will be able to detect human-written content in real time.

Modeling What-to-ask and How-to-ask for Answer-unaware Conversational Question Generation (2023.acl-long)

Copied to clipboard

Xuan Long Do, Bowei Zou, Shafiq Joty, Tran Tai, Liangming Pan, Nancy Chen, Ai Ti Aw

Natural Language Interfaces

Challenge:	Existing methods to generate conversational question are naive and do not account for the answer span.
Approach:	They propose a framework for generating a conversational question from a context.
Outcome:	The proposed framework achieves state-of-the-art in two different settings compared to existing models . it uses a sentence as the rationale and extracts the answer span from it .

Doolittle: Benchmarks and Corpora for Academic Writing Formalization (2023.emnlp-main)

Copied to clipboard

Shizhe Diao, Yongyu Lei, Liangming Pan, Tianqing Fang, Wangchunshu Zhou, Sedrick Keh, Min-Yen Kan, Tong Zhang

Logic-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoning (2023.findings-emnlp)

Challenge:	Existing methods of language refinement focus on narrow, specific linguistic features within isolated sentences, such as grammatical errors and improper word use.
Approach:	They propose a task to improve the overall quality of academic writing at paragraph level by integrating automatic feedback into the training process.
Outcome:	The proposed task improves the overall quality of formal academic writing at the paragraph level.

Copied to clipboard

Liangming Pan, Alon Albalak, Xinyi Wang, William Wang

CoHS-CQG: Context and History Selection for Conversational Question Generation (2022.coling-1)

Challenge:	Large Language Models (LLMs) have shown human-like reasoning abilities but struggle with complex logical problems.
Approach:	They propose a framework which integrates large language models with symbolic solvers to improve logical problem-solving by combining them with a self-refinement module.
Outcome:	The proposed framework improves logical problem-solving by integrating LLMs with symbolic solvers.

Copied to clipboard

Xuan Long Do, Bowei Zou, Liangming Pan, Nancy F. Chen, Shafiq Joty, Ai Ti Aw

Natural Language Interfaces

Challenge:	Existing studies focus on single-turn question generation, but few studies have studied the challenges of multiturn QG.
Approach:	They propose a two-stage conversational question generation framework that shortens the context and history of the input and calculates relevance scores.
Outcome:	The proposed framework achieves state-of-the-art on CoQA in answer-aware and answer-unaware settings.

Semantic Graphs for Generating Deep Questions (2020.acl-main)

Copied to clipboard

Liangming Pan, Yuxi Xie, Yansong Feng, Tat-Seng Chua, Min-Yen Kan

Multimodality

Challenge:	Existing research has focused on generating factoid questions relevant to one fact obtainable from a single sentence.
Approach:	They propose a framework that first constructs a semantic-level graph and then encodes it by introducing an attention-based GGNN.
Outcome:	The proposed framework captures the global structure of the document and facilitates reasoning over multiple facts.

The Knowledge Alignment Problem: Bridging Human and External Knowledge for Large Language Models (2024.findings-acl)

Copied to clipboard

Shuo Zhang, Liangming Pan, Junzhou Zhao, William Yang Wang

RuleArena: A Benchmark for Rule-Guided Reasoning with LLMs in Real-World Scenarios (2025.acl-long)

Challenge:	Large language models often ignore external knowledge to generate accurate answers . despite correct groundings, they can rely on wrong grounding or biases to hallucinate .
Approach:	They propose a framework that integrates human and human user clarifications to improve knowledge alignment.
Outcome:	The proposed framework improves model performance and mitigates hallucination by producing user-centered clarifications.

Copied to clipboard

Ruiwen Zhou, Wenyue Hua, Liangming Pan, Sitao Cheng, Xiaobao Wu, En Yu, William Yang Wang

How Is LLM Reasoning Distracted by Irrelevant Context? An Analysis Using a Controlled Benchmark (2025.emnlp-main)

Challenge:	RuleArena assesses the ability of large language models (LLMs) to follow complex, real-world rules in reasoning.
Approach:	They propose a benchmark to evaluate the ability of large language models (LLMs) to follow complex, real-world rules in reasoning.
Outcome:	The proposed benchmark covers airline baggage fees, NBA transactions, and tax regulations.

Copied to clipboard

Minglai Yang, Ethan Huang, Liang Zhang, Mihai Surdeanu, William Yang Wang, Liangming Pan

Robustness in NLP

Challenge:	Prior work has not explored the mechanisms underlying this sensitivity.
Approach:	They propose a synthetic benchmark to evaluate Large Language Models’ reasoning robustness against systematically controlled irrelevant context (IC).
Outcome:	The proposed model improves in-distribution and out-of-disttribution scenarios while training with strong distractors.

MAF: Multi-Aspect Feedback for Improving Reasoning in Large Language Models (2023.emnlp-main)

Copied to clipboard

Deepak Nathani, David Wang, Liangming Pan, William Wang

SciAgent: Tool-augmented Language Models for Scientific Reasoning (2024.emnlp-main)

Challenge:	Existing approaches to enhance Language Models fail to address diverse error types . generic feedback is a bottleneck for addressing diverse errors in reasoning chains .
Approach:	They propose an iterative refinement framework that integrates multiple feedback modules . they propose to address errors in reasoning chains by integrating frozen LMs with external tools .
Outcome:	The proposed framework improves performance in Mathematical Reasoning and Logical Entailment by 20% and 18% respectively.

Copied to clipboard

Yubo Ma, Zhibin Gou, Junheng Hao, Ruochen Xu, Shuohang Wang, Liangming Pan, Yujiu Yang, Yixin Cao, Aixin Sun

SCITAB: A Challenging Benchmark for Compositional Reasoning and Claim Verification on Scientific Tables (2023.emnlp-main)

Challenge:	SciAgent surpasses other LLMs with the comparable size by more than 8.0% in absolute accuracy.
Approach:	They propose a tool-augmented scientific reasoning setting that supplements LLMs with scalable toolsets and builds a benchmark to evaluate LLM’s abilities with tool assistance.
Outcome:	The proposed setting augments LLMs with scalable toolsets and shifts the focus from pursuing an omniscient problem solver to a proficient tool-user.

Copied to clipboard

Xinyuan Lu, Liangming Pan, Qian Liu, Preslav Nakov, Min-Yen Kan

AKEW: Assessing Knowledge Editing in the Wild (2024.emnlp-main)

Challenge:	Current scientific fact-checking benchmarks exhibit several shortcomings, such as biases arising from crowd-sourced claims and an over-reliance on text-based evidence.
Approach:	They present a dataset of 1.2K expert-verified scientific claims that require compositional reasoning for verification.
Outcome:	The proposed model outperforms existing models in table-based pretraining models and large language models.

Copied to clipboard

Xiaobao Wu, Liangming Pan, William Yang Wang, Anh Tuan Luu

Towards Intrinsic Interpretability of Large Language Models: A Survey of Design Principles and Architectures (2026.acl-long)

Challenge:	Recent Large Language Models (LLMs) have revolutionized the NLP field but their knowledge could become incorrect or outdated over time.
Approach:	They propose a new practical benchmark for knowledge editing that covers three editing settings of knowledge updates: structured facts, unstructured texts as facts, and extracted triplets.
Outcome:	The proposed method covers structured facts, unstructured texts as facts, and extracted triplets.

Copied to clipboard

Yutong Gao, Qinglin Meng, Yuan Zhou, Liangming Pan

Explainability & Interpretability in NLP

Challenge:	Existing studies on explainable AI focus on post-hoc explanation methods that interpret trained models through external approximations.
Approach:	They propose to categorize existing approaches into five design paradigms: functional transparency, concept alignment, representational decomposability, explicit modularization, and latent sparsity induction.
Outcome:	The proposed approaches are categorized into five design paradigms: functional transparency, concept alignment, representational decomposability, explicit modularization, and latent sparsity induction.

LEDOM: Reverse Language Model (2026.acl-long)

Copied to clipboard

Xunjian Yin, Sitao Cheng, Yuxi Xie, Xinyu Hu, Li Lin, Xinyi Wang, Liangming Pan, William Yang Wang, Xiaojun Wan

KQA Pro: A Dataset with Explicit Compositional Programs for Complex Question Answering over Knowledge Base (2022.acl-long)

Challenge:	Autoregressive language models are trained exclusively left-to-right, yet they are limited in their ability to factorize text.
Approach:	They propose a purely reverse autoregressive language model that factorizes text as a product of left-to-right conditionals.
Outcome:	The proposed model can be used to score forward outputs using reverse posterior estimates.

Copied to clipboard

Shulin Cao, Jiaxin Shi, Liangming Pan, Lunyiu Nie, Yutong Xiang, Lei Hou, Juanzi Li, Bin He, Hanwang Zhang

Natural Language Interfaces

Challenge:	Existing benchmarks for Complex KBQA lack compositional reasoning capabilities . Existing methods for Complex questions are poor in diversity or scale .
Approach:	They propose a compositional programming language to represent the reasoning process of complex questions.
Outcome:	The proposed dataset includes around 120K diverse natural language questions . it provides a compositional and interpretable programming language to represent the reasoning process of complex questions based on the proposed model .

Faithful Logical Reasoning via Symbolic Chain-of-Thought (2024.acl-long)

Copied to clipboard

Jundong Xu, Hao Fei, Liangming Pan, Qian Liu, Mong-Li Lee, Wynne Hsu

Machine Translation

Challenge:	SymbCoT is a framework that integrates symbolic expressions and logic rules with CoT prompting.
Approach:	They propose a Symbolic Chain-of-Thought framework that integrates symbolic expressions and logic rules with CoT prompting.
Outcome:	The proposed framework improves on 5 standard datasets with symbolic expressions and rules . it shows that it is more faithful, flexible, and explainable than the current method .

ConciseRL: Conciseness-Guided Reinforcement Learning for Efficient Reasoning Models (2025.findings-emnlp)

Copied to clipboard

Razvan-Gabriel Dumitru, Darius Peteleaza, Vikas Yadav, Liangming Pan