Papers with natural language
Learning as Abduction: Trainable Natural Logic Theorem Prover for Natural Language Inference (2020.starsem-1)
Copied to clipboard
| Challenge: | a logic-based approach to Natural Language Inference is becoming less and less common . a new method uses semantic relations to abduct sentences from data . |
| Approach: | They propose a method to reverse a theorem-proving procedure to abduct semantic relations from data. |
| Outcome: | The proposed method improves the performance of the theorem prover on the SICK dataset by 1.4% while maintaining high precision (>94%) |
Deep Bayesian Natural Language Processing (P19-4)
Copied to clipboard
| Challenge: | Introduction to deep Bayesian learning for natural language addresses the fundamentals of statistical models and neural networks. |
| Approach: | This tutorial addresses the advances in deep Bayesian learning for natural language . it focuses on advanced Bayessian models and deep models . authors present case studies and domain applications to tackle different issues . |
| Outcome: | This tutorial focuses on advanced Bayesian models and deep models for natural language . case studies and domain applications are presented to tackle different issues in deep Bayessian processing, learning and understanding. |
CoDesc: A Large Code–Description Parallel Dataset (2021.findings-acl)
Copied to clipboard
Masum Hasan, Tanveer Muttaqueen, Abdullah Al Ishtiaq, Kazi Sajeed Mehrab, Md. Mahim Anjum Haque, Tahmid Hasan, Wasi Ahmad, Anindya Iqbal, Rifat Shahriyar
| Challenge: | Existing models for natural language and programming languages are lagging behind due to a lack of large datasets and benchmarks. |
| Approach: | They present a large parallel dataset of Java methods and natural language descriptions that is used to train deep neural models. |
| Outcome: | The proposed dataset improves code summarization and code search by 22% and opens up possibilities for pretrained language models for Java. |
kNN-ICL: Compositional Task-Oriented Parsing Generalization with Nearest Neighbor In-Context Learning (2024.naacl-long)
Copied to clipboard
Wenting Zhao, Ye Liu, Yao Wan, Yibo Wang, Qingyang Wu, Zhongfen Deng, Jiangshu Du, Shuaiqi Liu, Yunlong Xu, Philip Yu
| Challenge: | Recent advances in task-oriented parsing involve formulating the task as a sequence-to-sequence problem, relying on a wealth of labeled data. |
| Approach: | They propose a task-oriented parsing framework that integrates nearest-neighbor learning with a nearest-nearest approach. |
| Outcome: | The proposed model can be used to synthesize computer programs based on a natural-language prompt without additional data or specialized prompts. |
MCoNaLa: A Benchmark for Code Generation from Multiple Natural Languages (2023.findings-eacl)
Copied to clipboard
| Challenge: | MCoNaLa benchmarks natural language code generation in languages that are not native to English. |
| Approach: | They propose to benchmark natural language code generation from natural language commands extending beyond English by using a multilingual dataset. |
| Outcome: | The proposed dataset compares natural language commands with code generation systems in three languages. |
LogiTorch: A PyTorch-based library for logical reasoning on natural language (2022.emnlp-demos)
Copied to clipboard
| Challenge: | Logical reasoning on natural language is one of the most challenging tasks for deep learning models. |
| Approach: | They propose a library that includes logical reasoning benchmarks and models . they use a dataset to run the library or fine tune the models with different hyperparameters . |
| Outcome: | This library includes logical reasoning benchmarks, models, utility functions and co-reference resolution. |
A Perspective on LLM Data Generation with Few-shot Examples: from Intent to Kubernetes Manifest (2025.acl-industry)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have transformed how complex tasks can be automated . traditional cloud computing operations involve complex manual configurations . |
| Approach: | They propose a pipeline for generating K8s manifests directly from user-described intents expressed in natural language using LLMs. |
| Outcome: | The proposed pipeline can generate K8s manifests directly from user-described intents expressed in natural language using LLMs. |
Towards Transparent Interactive Semantic Parsing via Step-by-Step Correction (2022.findings-acl)
Copied to clipboard
| Challenge: | Existing studies on semantic parsing focus on mapping a natural-language utterance to a logical form (LF) but natural language may contain ambiguity and variability, making this challenge difficult. |
| Approach: | They propose an interactive semantic parsing framework that explains the predicted LF step by step in natural language and enables the user to make corrections through natural-language feedback for individual steps. |
| Outcome: | The proposed framework improves parsing accuracy and transparency in a crowdsourced dialogue dataset. |
Prompt2Model: Generating Deployable Models from Natural Language Instructions (2023.emnlp-demo)
Copied to clipboard
| Challenge: | Large language models (LLMs) are a step backward from traditional special-purpose NLP models . they require extensive computational resources for deployment and can be gated behind APIs . |
| Approach: | They propose a general-purpose method that takes a natural language task description and uses it to train a special-purpose model. |
| Outcome: | The proposed method outperforms a strong LLM by 20% while being 700 times smaller. |
Using Intermediate Representations to Solve Math Word Problems (P18-1)
Copied to clipboard
| Challenge: | Existing approaches to solving math word problems do not include higher-order operations that cannot be explicitly represented in equations. |
| Approach: | They propose an iterative labeling framework that generates intermediate forms and executes them to obtain the final answers. |
| Outcome: | The proposed model outperforms existing models in solving math word problems. |
DivLogicEval: A Framework for Benchmarking Logical Reasoning Evaluation in Large Language Models (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing logic reasoning benchmarks are limited in language diversity and their distributions are deviated from ideal distributions, which may lead to biased evaluation results. |
| Approach: | They propose a new logic benchmark DivLogicEval that uses natural sentences to evaluate logical reasoning . |
| Outcome: | The proposed evaluation metric mitigates bias and randomness inherent in LLMs. |
SQLGenie: A Practical LLM based System for Reliable and Efficient SQL Generation (2025.acl-industry)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) enable natural language to SQL conversion, but generating accurate, efficient queries is challenging due to ambiguous intent, domain knowledge requirements and database constraints. |
| Approach: | They propose a system for reliable SQL generation that integrates Table Onboarder, SQL Generator and Feedback Augmentation. |
| Outcome: | The proposed system surpasses the best single-LLM baseline by 21.5% and the strongest pipeline competitor by 5.3% on public benchmarks and internal datasets. |
How Many Data Samples is an Additional Instruction Worth? (2023.findings-eacl)
Copied to clipboard
| Challenge: | Recent introduced instruction-paradigm empowers non-expert users to leverage NLP resources by defining a new task in natural language. |
| Approach: | They propose to define a task in natural language without creating task-specific datasets or building models. |
| Outcome: | The proposed model outperforms multitask learning models but is far from state-of-the-art task-specific models. |
Text-Transport: Toward Learning Causal Effects of Natural Language (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for causal inference require strong assumptions about the data, meaning the data from which one *can* estimate valid causal effects is not representative of the actual target domain of interest. |
| Approach: | They propose a method for estimation of causal effects from natural language under any text distribution using the notion of distribution shift. |
| Outcome: | The proposed method can be used to estimate causal effects from natural language under any text distribution. |
Exploring Decomposition for Table-based Fact Verification (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing research focuses on fact verification based on unstructured text, but structured data is becoming more prevalent. |
| Approach: | They propose to decompose complex statements into simpler subproblems to improve table-based verification by a weakly supervised parser. |
| Outcome: | The proposed method achieves state-of-the-art accuracy on the TabFact benchmark. |
Great~Truths~are ~Always ~Simple: A Rather Simple Knowledge Encoder for Enhancing the Commonsense Reasoning Capacity of Pre-Trained Models (2022.findings-naacl)
Copied to clipboard
| Challenge: | Existing approaches to enhance pre-trained language models (PTMs) with a knowledge-aware graph neural network (GNN) encoder that models a commonsense knowledge graph (CSKG) can't explain how external knowledge resources improve the reasoning capacity of PTMs. |
| Approach: | They propose to use relation features from CSKGs to enhance the reasoning capacity of pre-trained language models (PTMs) by encoding a commonsense knowledge graph (CSKG) |
| Outcome: | The proposed approach reduces the parameters for encoding CSKGs and improves on five benchmarks. |
Exploring Data Augmentation in Neural DRS-to-Text Generation (2024.eacl-long)
Copied to clipboard
| Challenge: | Neural networks are notoriously data-hungry, resulting in ungrammatical texts . data augmentation requires a specific design for a structurally rich input format . |
| Approach: | They propose to selectively augment a training set with new data by adding and varying two specific lexical categories, i.e. proper and common nouns. |
| Outcome: | The proposed approach selectively augments a training set with new data by adding and varying two specific lexical categories, i.e. proper and common nouns. |
Speak to your Parser: Interactive Text-to-SQL with Natural Language Feedback (2020.acl-main)
Copied to clipboard
| Challenge: | a natural language interface (NLI) can be used to correct semantic parsing errors . human correction accuracy is 81.5%, but the best model achieves only 25.1% . |
| Approach: | They propose a task where humans can provide free-form natural language feedback to correct a system when it generates an inaccurate interpretation of an initial utterance. |
| Outcome: | The proposed model improves the parsing accuracy while maintaining flexibility of natural language interaction. |
CVE-Bench: Benchmarking LLM-based Software Engineering Agent’s Ability to Repair Real-World CVE Vulnerabilities (2025.naacl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) and LLM agents have demonstrated significant potential in this domain by understanding descriptions in natural language and generating corresponding formal code. |
| Approach: | They propose an evaluation framework that provides LLM agents with a test environment that simulates the real-world vulnerability repair process. |
| Outcome: | The proposed framework can repair 21% of vulnerabilities at its best, but lacks expert knowledge . the evaluation framework can only repair 29% of vulnerabilities, but it can be used in real-world scenarios . |
Efficient Constituency Tree based Encoding for Natural Language to Bash Translation (2022.naacl-main)
Copied to clipboard
| Challenge: | Semantic parsing is one of the central tasks for natural language understanding (NLU). |
| Approach: | They propose a Segmented Invocation Transformer that utilizes the information from the constituency parse tree of the natural language text and Bash command components to generate Bash commands. |
| Outcome: | The proposed method improves the inference time and reduces the model parameters by 1.8x . |
Natural Language to Code Translation with Execution (2022.emnlp-main)
Copied to clipboard
| Challenge: | Generative code models do not explicitly incorporate program semantics during training, but they are able to generate correct solutions for many problems. |
| Approach: | They introduce execution result-based minimum Bayes risk decoding for program selection . they select output programs from a generated candidate set by marginalizing over implementations that share the same semantics . |
| Outcome: | The proposed model outperforms all other methods on natural language-to-code translation. |
Improving Segmentation for Technical Support Problems (2020.acl-main)
Copied to clipboard
| Challenge: | Technical support problems are long and complex and cannot be correctly parsed by tools designed for natural language. |
| Approach: | They propose a sequence labelling task and a supervised text segmentation approach to solve this problem. |
| Outcome: | The proposed approach improves on the downstream task of answer retrieval. |
PreFLMR: Scaling Up Fine-Grained Late-Interaction Multi-modal Retrievers (2024.acl-long)
Copied to clipboard
| Challenge: | Large Multimodal Models excel in natural language and visual understanding but are challenged by challenging tasks such as Knowledge-based Visual Question Answering (KB-VQA). |
| Approach: | They propose a framework for training Large Multimodal Models (LMMs) to perform KB-VQA tasks. |
| Outcome: | The proposed framework is used to train and evaluate multi-modal retrievers. |
Addressing Resource and Privacy Constraints in Semantic Parsing Through Data Augmentation (2022.findings-acl)
Copied to clipboard
| Challenge: | a low-resource task-oriented semantic parser is limited by privacy requirements for unlabeled natural utterances. |
| Approach: | They propose a setup for low-resource task-oriented semantic parsing based on user interactions . they use structured canonical utterances, then simulating corresponding natural language to improve performance. |
| Outcome: | The proposed setup improves on a low-resource task-oriented semantic parser using utterances collected through user interactions. |
CodePrompt: Task-Agnostic Prefix Tuning for Program and Language Generation (2023.findings-acl)
Copied to clipboard
| Challenge: | Prompt-tuning methods have been used to solve inefficient parameter update and storage issues in Natural Language Generation tasks. |
| Approach: | They propose a task-agnostic prompt tuning method that reflects the traits of PLM for program language. |
| Outcome: | The proposed method is effective in three PLG tasks, not only in the full-data setting but also in the low-resource setting and cross-domain setting. |
Optimus: Organizing Sentences via Pre-trained Modeling of a Latent Space (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing models for language understanding and understanding can be trained to provide contextualized representations of words based on text data. |
| Approach: | They propose a large-scale language VAE model Optimus that is pre-trained on large text corpus and fine-tuned for various language generation and understanding tasks. |
| Outcome: | The proposed model achieves new state-of-the-art on VAE language modeling benchmarks. |
Leakage-Adjusted Simulatability: Can Models Generate Non-Trivial Explanations of Their Behavior in Natural Language? (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Existing models that generate NL explanations for tasks have been evaluated on the basis of surface-level similarities to human explanations, both through automatic metrics like BLEU and human evaluations. |
| Approach: | They propose to use a model as a proxy for a human observer to evaluate NL explanations from the model simulatability perspective. |
| Outcome: | The proposed model-generated explanations are evaluated on the basis of surface-level similarities to human explanations, both through automatic metrics like BLEU and human evaluations. |
Follow the Beaten Path: The Role of Route Patterns on Vision-Language Navigation Agents Generalization Abilities (2025.naacl-long)
Copied to clipboard
| Challenge: | Vision and language navigation (VLN) is a challenging task towards the creation of embodied agents. |
| Approach: | They propose a solution that combines visual and linguistic features to enable VLN . they propose augmentation of the training data to fill the gap in missing patterns . |
| Outcome: | The proposed solution fills the gap in missing patterns of training data. |
Implicit Deep Latent Variable Models for Text Generation (D19-1)
Copied to clipboard
| Challenge: | Variational auto-encoders have been used for text generation but their representation power is limited due to two reasons. |
| Approach: | They advocate sample-based representations of variational distributions for natural language . they further develop an LVM to directly match the aggregated posterior to the prior . |
| Outcome: | The proposed model can be viewed as a natural extension of VAEs with a regularization of maximizing mutual information, mitigating the "posterior collapse" issue. |
Beyond Seen Data: Improving KBQA Generalization Through Schema-Guided Logical Form Generation (2025.emnlp-main)
Copied to clipboard
| Challenge: | Knowledge base question answering (KBQA) aims to answer user questions in natural language using rich human knowledge stored in large KBs. |
| Approach: | They propose a model that injects schema contexts into entity retrieval and logical form generation to enhance generalizability. |
| Outcome: | The proposed model outperforms state-of-the-art models on two commonly used benchmark datasets across a variety of test settings. |
Code and Named Entity Recognition in StackOverflow (2020.acl-main)
Copied to clipboard
| Challenge: | StackOverflow has 15 million programming related questions written by 8.5 million users . however, there is a lack of fundamental NLP resources and techniques for identifying software-related named entities within natural language sentences. |
| Approach: | They propose a named entity recognition corpus for the computer programming domain with 15,372 sentences annotated with 20 fine-grained entity types. |
| Outcome: | The proposed model improves on 152 million sentences from StackOverflow and achieves 79.10 F-1 score for code and named entity recognition. |
Countering Language Drift via Visual Grounding (D19-1)
Copied to clipboard
| Challenge: | Emergent multi-agent communication protocols are different from natural language . a long-standing goal of artificial intelligence research is to develop agents that can cooperate with other agents . |
| Approach: | They propose to use syntactic and semantic constraints to improve communication . they propose to combine these constraints with auxiliary training constraints to reduce language drift . |
| Outcome: | a new study shows that pre-trained agents retain English syntax while learning to convey intended meaning . the proposed training constraints can be used to mitigate language drift . |
What Have We Achieved on Non-autoregressive Translation? (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing studies have shown that non-autoregressive (NAT) methods underperform autoregressive methods (AT) however, their evaluation using BLEU has been shown to weakly correlate with human annotations. |
| Approach: | They propose to evaluate four representative NAT methods using BLEU to narrow the performance gap between autoregressive and autoregressive translations. |
| Outcome: | The proposed methods underperform NAT and autoregressive methods under more reliable evaluation metrics. |
Emergence of Hierarchical Reference Systems in Multi-agent Communication (2022.coling-1)
Copied to clipboard
| Challenge: | a hierarchical reference system allows the selection of the most appropriate level of specificity for a given context. |
| Approach: | They propose a hierarchical reference game to study the emergence of hierarchic reference systems in artificial agents. |
| Outcome: | The proposed game shows that agents can generalize to new concepts . the hierarchical reference game is based on a simplified world . |
Beyond Recognising Entailment: Formalising Natural Language Inference from an Argumentative Perspective (2024.acl-long)
Copied to clipboard
| Challenge: | Existing methods for recognizing textual entailment lack a standardized definition of inference, making it difficult to compare methods trained on different datasets. |
| Approach: | They propose a rigorous approach to align entailment recognition with argumentation theory by using a tool to assist humans in annotating arguments according to the PTA. |
| Outcome: | The proposed model is based on a human-trained dataset and provides insights into non-expert annotator training. |
SYSML: StYlometry with Structure and Multitask Learning: Implications for Darknet Forum Migrant Analysis (2021.emnlp-main)
Copied to clipboard
| Challenge: | Crypto markets are forums where goods and services are exchanged between parties who use encryption to conceal their identities. |
| Approach: | They propose a stylometry-based multitask learning approach for natural language and model interactions using graph embeddings. |
| Outcome: | The proposed approach outperforms existing methods in four darknet forums with a lift of up to 2.5X on the mean retrieval rank and 2X on recall@10. |
A Geometry-Inspired Attack for Generating Natural Language Adversarial Examples (2020.coling-main)
Copied to clipboard
| Challenge: | Existing techniques to generate adversarial examples for natural language are limited . previous research on adversarials focused on images, but this is not the case with natural language. |
| Approach: | They propose a geometry-inspired attack for generating natural language adversarial examples . they use deep neural networks to iteratively approximate the decision boundary . |
| Outcome: | The proposed attack fools natural language models with high success rates while replacing a few words. |
Understanding Programs by Exploiting (Fuzzing) Test Cases (2023.findings-acl)
Copied to clipboard
| Challenge: | Semantic understanding of programs has attracted great attention in the community . large language models (LLMs) are capable of learning contextual information from data at scale . |
| Approach: | They propose to incorporate a relationship between inputs and possible outputs into learning for achieving a deeper semantic understanding of programs. |
| Outcome: | The proposed method outperforms current state-of-the-art on two programming tasks and outperformed current state of the art by large margins. |
CodeFusion: A Pre-trained Diffusion Model for Code Generation (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing models for code generation from natural language do not allow reconsidering earlier tokens . prior work has explored grouped beam search or nucleus sampling to generate diverse text. |
| Approach: | They propose a diffusion code generation model that iteratively denoises a program conditioned on the encoded natural language. |
| Outcome: | The proposed model outperforms state-of-the-art models in accuracy and diversity compared to existing models. |
MUCAR: Benchmarking Multilingual Cross-Modal Ambiguity Resolution for Multimodal Large Language Models (2025.emnlp-main)
Copied to clipboard
Xiaolong Wang, Zhaolu Kang, Wangyuxuan Zhai, Xinyue Lou, Yunghwei Lai, Ziyue Wang, Yawen Wang, Kaiyu Huang, Yile Wang, Peng Li, Yang Liu
| Challenge: | Existing multimodal benchmarks overlook linguistic and visual ambiguities, authors say . ambiguity resolution between modalities is lacking in multimodal large language models . |
| Approach: | They propose a benchmark to evaluate multimodal ambiguity resolution across multilingual and cross-modal scenarios. |
| Outcome: | a new benchmark evaluates multimodal ambiguity resolution across multilingual and cross-modal scenarios . the benchmark shows that MLLMs can resolve ambiguities in image-text alignment . however, existing benchmarks often overlook linguistic and visual ambiguties . |
Question Answering as Programming for Solving Time-Sensitive Questions (2023.emnlp-main)
Copied to clipboard
| Challenge: | Recent studies show that Large Language Models (LLMs) have shown remarkable intelligence in question answering. |
| Approach: | They propose to reframe the Question Answering task as Programming to overcome this limitation by leveraging LLMs' superior ability in understanding both natural language and programming language. |
| Outcome: | The proposed approach improves on time-sensitive question answering datasets by 14.5% over baselines. |
Symbolic Working Memory Enhances Language Models for Complex Rule Application (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) excel in single-step rule application but struggle with multi-step deductive reasoning when rules are presented non-sequentially. |
| Approach: | They propose to augment LLMs with external working memory and introduce a neurosymbolic framework for rule application that stores facts and rules in both natural language and symbolic forms, enabling precise tracking. |
| Outcome: | The proposed framework iteratively performs symbolic rule grounding and LLM-based rule implementation. |
DocCGen: Document-based Controlled Code Generation (2024.emnlp-main)
Copied to clipboard
Sameer Pimparkhede, Mehant Kammakomati, Srikanth Tamilselvam, Prince Kumar, Ashok Kumar, Pushpak Bhattacharyya
| Challenge: | Large language models (LLMs) produce state-of-the-art performance on natural language to code generation for resource-rich general-purpose languages like C++, Java, and Python. |
| Approach: | They propose a framework that breaks the NL-to-Code generation task into two steps . they use library documentation to detect the correct libraries and schema rules extracted from the documentation to constrain the decoding . |
| Outcome: | The proposed framework improves different sized language models across all six evaluation metrics, reducing syntactic and semantic errors in structured code. |
Seeing Beyond Words: MatVQA for Challenging Visual-Scientific Reasoning in Materials Science (2026.findings-acl)
Copied to clipboard
| Challenge: | Multimodal Large Language Models (MLLMs) outperform existing benchmarks in both natural language and coding domains. |
| Approach: | They propose a scalable benchmark that integrates vision and language modalities to address this gap by eliminating textual shortcuts. |
| Outcome: | The new benchmark outperforms existing benchmarks in both natural language and coding domains. |
MultiTEND: A Multilingual Benchmark for Natural Language to NoSQL Query Translation (2025.findings-acl)
Copied to clipboard
| Challenge: | Recent advances in NoSQL database support focus on English . however, the intricacy and heterogeneity of NoSqL query languages present a formidable challenge . |
| Approach: | They propose a multilingual benchmark for natural language to NoSQL query generation that covers six languages. |
| Outcome: | The proposed framework improves performance in English and non-English settings, while ignoring lexical and syntactic differences. |
Profiler: Black-box AI-generated Text Origin Detection via Context-aware Inference Pattern Analysis (2025.emnlp-main)
Copied to clipboard
Hanxi Guo, Siyuan Cheng, Xiaolong Jin, Zhuo Zhang, Guangyu Shen, Kaiyuan Zhang, Shengwei An, Guanhong Tao, Xiangyu Zhang
| Challenge: | Existing methods to identify the origin of AI-generated texts fail to identify origin due to the high similarity of different LLMs. |
| Approach: | They propose a black-box AI-generated text origin detection method which accurately predicts the origin of an input text by extracting distinct context inference patterns. |
| Outcome: | The proposed method outperforms 10 state-of-the-art baselines and achieves a 25% increase in AUC score on average across natural language and code datasets. |
CODEPROMPTZIP: Code-specific Prompt Compression for Retrieval-Augmented Generation in Coding Tasks with LMs (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing prompt compression techniques for natural language lack fine-grained control over compression ratios. |
| Approach: | They propose a code-aware prompt compression framework for RAG that enables precise length control while preserving critical information. |
| Outcome: | The proposed framework outperforms baselines on three code-related tasks while maintaining the most informative tokens. |
RIMRULE: Improving Tool-Using Language Agents via MDL-Guided Rule Learning (2026.acl-long)
Copied to clipboard
Xiang Gao, Yuguang Yao, Qi Zhang, Kaiwen Dong, Avinash Baidya, Ruocheng Guo, Hilaf Hasson, Kamalika Das
| Challenge: | Large language models (LLMs) struggle to use tools reliably in domain-specific settings. |
| Approach: | They propose a neuro-symbolic approach to adapt large language models to task-specific tools . they propose reusable rules that are distilled from failure traces and injected into the prompt . |
| Outcome: | Experiments show that the proposed approach outperforms prompting-based adaptation methods and complements finetuning. |
NoisyCausal: A Benchmark for Evaluating Causal Reasoning Under Structured Noise (2026.acl-long)
Copied to clipboard
| Challenge: | Existing benchmarks focus on clean, abstract scenarios where causal structure is simple or implicitly assumed. |
| Approach: | They propose a benchmark to evaluate causal reasoning under structured noise. |
| Outcome: | The proposed method outperforms standard prompting and reasoning baselines on NoisyCausal. |