Papers by Ali Payani

14 papers
How Can Input Reformulation Improve Tool Usage Accuracy in a Complex Dynamic Environment? A Study on tau-bench (2025.findings-emnlp)

Copied to clipboard

Challenge: Recent advances in reasoning and planning capabilities of large language models have enabled their potential as autonomous agents capable of tool use in dynamic environments.
Approach: They propose an input-reformulation multi-agent framework that reformulates user queries .
Outcome: The proposed framework outperforms ReAct, Function Calling, and Self-Reflection in overall pass5 scores.
FAMA: Failure-Aware Meta-Agentic Framework for Open-Source LLMs in Interactive Tool Use Environments (2026.findings-acl)

Copied to clipboard

Challenge: Large Language Models are being increasingly deployed as decision-making core of autonomous agents . however, in conversational benchmarks, these agents fail due to the cascading effects of incorrect decision- making .
Approach: They propose a framework that analyzes failure trajectories from baseline agents to identify most prevalent errors.
Outcome: Experiments show that the framework improves performance over open-source LLMs . the framework can be used to build reliable, multi-turn tool-use agents .
MDBench: A Synthetic Multi-Document Reasoning Benchmark Generated with Knowledge Guidance (2025.findings-acl)

Copied to clipboard

Challenge: Multi-document reasoning is an area of increasing relevance given LLM capabilities in handling longer-context inputs, but few benchmarks exist to rigorously examine model behavior in this setting.
Approach: They propose a new dataset for evaluating LLMs on the task of multi-document reasoning that uses condensed structured seed knowledge to modify it through LLM-assisted edits.
Outcome: The proposed method generates document sets and QA examples on a multi-document reasoning task using a synthetic generation process.
Harnessing the Power of Large Language Models for Natural Language to First-Order Logic Translation (2024.acl-long)

Copied to clipboard

Challenge: Logic-based approaches to reasoning have lost popularity due to limited scalability and coverage.
Approach: They present a dataset of 28K sentence-level NL-FOL pairs from GPT4 and a LogicLLaMA2-7B/13B fine-tuned on MALLS for NL translation.
Outcome: The proposed model can be used standalone or to correct previously generated rules by GPT3.5.
When is Tree Search Useful for LLM Planning? It Depends on the Discriminator (2024.acl-long)

Copied to clipboard

Challenge: Existing methods to build language agents that can plan efficiently and accurately have not met the needs of advanced planning methods to achieve such improvements.
Approach: They propose to use iterative correction and tree search to solve multi-step problems in a language agent framework with three components: a generator, a discriminator, and a planning method.
Outcome: The proposed methods improve performance on two tasks, text-to-SQL parsing and mathematical reasoning, while using discriminators with 90% accuracy.
Large Language Models Can Learn Temporal Reasoning (2024.acl-long)

Copied to clipboard

Challenge: Temporal reasoning (TR) is a fundamental ability of large language models (LLMs) however, there is neo-standard methods to perform TR, which are not suitable for large language model applications.
Approach: They propose a framework to enhance temporal reasoning by using a latent representation, temporal graph (TG) instead of reasoning over the original context, they adopt a temporal representation that enhances TR learning.
Outcome: The proposed framework improves the learning of language-based TR by incorporating a latent representation, temporal graph (TG) a synthetic dataset is constructed for fine-tuning LLMs on text-to-TG translation tasks and benchmarks.
Large Vision-Language Model Alignment and Misalignment: A Survey Through the Lens of Explainability (2025.findings-emnlp)

Copied to clipboard

Challenge: Large Vision-Language Models have demonstrated remarkable capabilities in processing both visual and textual information.
Approach: They examine the challenge of alignment and misalignment in LVLMs through an explainability lens.
Outcome: The findings highlight the need for standardized evaluation protocols and in-depth explainability studies.
Beyond Semantic Entropy: Boosting LLM Uncertainty Quantification with Pairwise Semantic Similarity (2025.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) generate long one-sentence responses that are less effective because they overlook two crucial factors: intra-cluster similarity and inter-c cluster similarity.
Approach: They propose a method that generalizes semantic entropy and uses token probabilities to quantify uncertainty in large language models.
Outcome: The proposed method can be extended to white-box settings by incorporating token probabilities.
Text-to-SQL Error Correction with Language Models of Code (2023.acl-short)

Copied to clipboard

Challenge: Existing semantic parsers are not accurate enough for use in text-to-SQL parsing tasks.
Approach: They propose to build clause-level edit models to correct SQL queries instead of token-level ones.
Outcome: The proposed model improves the exact set match accuracy of different parsers by 2.4-6.5 and obtains up to 4.3 point absolute improvement over two strong baselines.
Can LLMs Reason in the Wild with Programs? (2024.findings-emnlp)

Copied to clipboard

Challenge: Large language models have shown superior capability to solve reasoning problems with programs.
Approach: They propose a task where an LLM is tasked to solve a reasoning problem of unknown type by identifying the sub-problems and their corresponding formalisms.
Outcome: The proposed model can be fine tuned to achieve better performance on ambiguous and mixed scope problems.
Investigating the Shortcomings of LLMs in Step-by-Step Legal Reasoning (2025.findings-naacl)

Copied to clipboard

Challenge: Reasoning abilities of LLMs have been a key focus in recent years.
Approach: They propose to use a college-level Multiple Choice Question-Answering task to identify LLM errors and evaluate their performance.
Outcome: The proposed framework can be used in detailed error analysis of reasoning chains for logic-intensive complex tasks.
AutoSDT: Scaling Data-Driven Discovery Tasks Toward Open Co-Scientists (2025.emnlp-main)

Copied to clipboard

Challenge: AutoSDT-5K is the only automatically collected and the largest open dataset for data-driven scientific discovery.
Approach: They propose an automatic pipeline that collects high-quality coding tasks in real-world data-driven discovery workflows.
Outcome: The proposed pipeline synthesizes accurate tasks and tasks from a dataset of 5,404 tasks covering four scientific disciplines and 756 Python packages.
SAE-SSV: Supervised Steering in Sparse Representation Spaces for Reliable Control of Language Models (2025.emnlp-main)

Copied to clipboard

Challenge: Large language models (LLMs) have impressive capabilities in natural language understanding and generation, but controlling their behavior remains a challenge.
Approach: They propose a supervised steering approach that operates in sparse, interpretable representation spaces.
Outcome: The proposed approach achieves higher success rates with minimal degradation in generation quality compared to existing methods.
Deliberate Reasoning in Language Models as Structure-Aware Planning with an Accurate World Model (2025.acl-long)

Copied to clipboard

Challenge: Existing Chain-of-Thought (CoT) methods struggle with consistency and verification in complex reasoning tasks.
Approach: They propose a framework that integrates structured knowledge representation with learned planning.
Outcome: The proposed framework outperforms existing Chain-of-Thought (CoT) methods on math reasoning, logical reasoning, and coding tasks.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations