Papers with GPT-3.5-Turbo
STAND-Guard: A Small Task-Adaptive Content Moderation Model (2025.coling-industry)
Copied to clipboard
| Challenge: | Content moderation is important for developing welcoming online platforms and responsible large language models. |
| Approach: | They propose a small task-adaptive coNtent moDeration model that can be easily adapted to new or customized content moderation tasks without extensive model tuning. |
| Outcome: | The proposed model is comparable to GPT-3.5-Turbo on unseen English binary classification tasks. |
Learning Planning-based Reasoning by Trajectories Collection and Process Reward Synthesizing (2024.emnlp-main)
Copied to clipboard
| Challenge: | Recent studies have raised concerns regarding the hallucination and flaws in their reasoning process. |
| Approach: | They propose a framework to learn planning-based reasoning through Direct Preference Optimization on collected trajectories, which are ranked according to synthesized process rewards. |
| Outcome: | The proposed model surpasses GPT-3.5-Turbo on logical reasoning benchmarks on a set of logically-based reasoning tasks. |
FaithBench: A Diverse Hallucination Benchmark for Summarization by Modern LLMs (2025.naacl-short)
Copied to clipboard
Forrest Sheng Bao, Miaoran Li, Renyi Qu, Ge Luo, Erana Wan, Yujia Tang, Weisi Fan, Manveer Singh Tamber, Suleman Kazi, Vivek Sourabh, Mike Qi, Ruixuan Tu, Chenyu Xu, Matthew Gonzales, Ofer Mendelevitch, Amin Ahmad
| Challenge: | Existing evaluations of hallucinations in large language models suffer from a lack of diversity and recency in the LLM and LLM families considered. |
| Approach: | They propose a summarization hallucination benchmark that challenges models to disagree on hallucines . they use models to generate answers or summaries from textual input . |
| Outcome: | The proposed model combines the best of 10 modern LLMs with ground truth annotations. |
SeRTS: Self-Rewarding Tree Search for Biomedical Retrieval-Augmented Generation (2024.findings-emnlp)
Copied to clipboard
Minda Hu, Licheng Zong, Hongru Wang, Jingyan Zhou, Jingjing Li, Yichen Gao, Kam-Fai Wong, Yu Li, Irwin King
| Challenge: | Existing retrieval-augmented approaches to large language models face performance limitations due to the lack of publicly available training data. |
| Approach: | They propose a plug-and-play LLM-based retrieval method called Self-Rewarding Tree Search based on Monte Carlo Tree Search and a self-rewarding paradigm to address these limitations. |
| Outcome: | The proposed method improves the performance of the BM25 retriever and surpasses the baseline of self-reflection in both efficiency and scalability. |
Mixed Distillation Helps Smaller Language Models Reason Better (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Recent large language models (LLMs) have demonstrated impressive multiple step-by-step reasoning capabilities in recent NLP reasoning tasks. |
| Approach: | They propose a mixed distillation framework that distills multiple step-by-step reasoning abilities into smaller language models (SLMs) they leverage LLMs to generate multiple step by step reasoning rationales by sampling automatically. |
| Outcome: | The proposed framework outperforms existing models on SVAMP, GSM8K and ASDIV, while a single model generated by MD exceeds the comprehensive performance of two individual CoT and PoT distilled models. |
LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression (2024.acl-long)
Copied to clipboard
| Challenge: | Longer prompts introduce irrelevant and redundant information, which can weaken LLMs' performance. |
| Approach: | They propose a prompt compression tool that improves LLMs' perception of key information in input prompts by up to 21.4% with around 4x fewer tokens in GPT-3.5-Turbo. |
| Outcome: | The proposed solution improves performance and reduces costs and latency by up to 21.4% with around 4x fewer tokens in the NaturalQuestions benchmark. |
Visual Editing with LLM-based Tool Chaining: An Efficient Distillation Approach for Real-Time Applications (2024.emnlp-industry)
Copied to clipboard
| Challenge: | Using natural language as an interaction medium for video editing can mitigate the complexity of video editing. |
| Approach: | They propose a method to fine-tune LLMs for invoking tools in real-time applications by interpreting user stylistic requests in natural language. |
| Outcome: | The proposed model matches the performance of the teacher model significantly, reducing costs and latency. |
Assessing LLMs for Zero-shot Abstractive Summarization Through the Lens of Relevance Paraphrasing (2025.findings-naacl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have achieved state-of-the-art performance at zero-shot summarization of abstractive summaries for given articles, but little is known about their robustness at this task. |
| Approach: | They propose a strategy that uses the most relevant sentences to generate an ideal summary and then paraphrases them to obtain a minimally perturbed dataset. |
| Outcome: | The proposed approach can be used to measure the robustness of LLMs as summarizers on a minimally perturbed dataset. |
Iterative Refinement of Project-Level Code Context for Precise Code Generation with Compiler Feedback (2024.findings-acl)
Copied to clipboard
Zhangqian Bi, Yao Wan, Zheng Wang, Hongyu Zhang, Batu Guan, Fangxin Lu, Zili Zhang, Yulei Sui, Hai Jin, Xuanhua Shi
| Challenge: | Large Language Models (LLMs) generate code for given contexts, such as incomplete code, class, data structure, or project-specific information. |
| Approach: | They propose a compiler feedback-based code generation approach that leverages static analysis to identify mismatches between the generated code and the project's context. |
| Outcome: | The proposed model outperforms retrieval-based code generation baselines and significantly outperfies the existing large language models. |
MEGAVERSE: Benchmarking Large Language Models Across Languages, Modalities, Models and Tasks (2024.naacl-long)
Copied to clipboard
Sanchit Ahuja, Divyanshu Aggarwal, Varun Gumma, Ishaan Watts, Ashutosh Sathe, Millicent Ochieng, Rishav Hada, Prachi Jain, Mohamed Ahmed, Kalika Bali, Sunayana Sitaram
| Challenge: | Several new LLMs have been introduced necessitating their evaluation on non-English languages. |
| Approach: | They perform a thorough evaluation of the non-English capabilities of SoTA LLMs by comparing them on the same set of multilingual datasets. |
| Outcome: | The proposed model outperforms models on multilingual datasets on 22 languages including low-resource African languages. |
METAL: Towards Multilingual Meta-Evaluation (2024.findings-naacl)
Copied to clipboard
| Challenge: | Recent studies show that Large Language Models excel on many standard NLP benchmarks. |
| Approach: | They propose a framework for end-to-end evaluation of Large Language Models as evaluators in multilingual scenarios. |
| Outcome: | The proposed framework evaluates LLMs as evaluators in multilingual scenarios. |
ProTrix: Building Models for Planning and Reasoning over Tables with Sentence Context (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Tables are a crucial tool for organizing and presenting information in various domains. |
| Approach: | They propose a Plan-then-Reason framework to answer different types of user queries over tables with sentence context. |
| Outcome: | The proposed framework outperforms existing frameworks without self-consistency while using less API calls and in-context demonstrations. |
An Optimizable Suffix Is Worth A Thousand Templates: Efficient Black-box Jailbreaking without Affirmative Phrases via LLM as Optimizer (2025.findings-naacl)
Copied to clipboard
| Challenge: | Existing jailbreaking methods generate harmful and unethical content when subjected to jailbreaking attacks. |
| Approach: | They propose a black-box jailbreaking method with optimizable suffixes that translate jailbreaking objectives into natural language instructions. |
| Outcome: | The proposed method outperforms existing methods by 2.4 times in the ASR of three open-source LLMs and GPT-3.5-Turbo. |
Stronger Universal and Transferable Attacks by Suppressing Refusals (2025.naacl-long)
Copied to clipboard
| Challenge: | Efforts have focused on aligning models to human preferences (RLHF) . yet, it is believed that such optimization-based attacks are sample-specific. |
| Approach: | They propose an algorithm to embed a "safety feature" into models to make them safe for mass deployment. |
| Outcome: | The proposed attack achieves 25% success rate against the state-of-the-art Circuit Breaker defense, compared to 2.5% by white-box GCG. |
StatBot.Swiss: Bilingual Open Data Exploration in Natural Language (2024.findings-acl)
Copied to clipboard
Farhad Nooralahzadeh, Yi Zhang, Ellery Smith, Sabine Maennel, Cyril Matthey-Doret, Raphaël De Fondeville, Kurt Stockinger
| Challenge: | StatBot.Swiss dataset is the first bilingual benchmark for evaluating Text-to-SQL systems based on real-world applications. |
| Approach: | They propose to use a bilingual dataset to evaluate LLMs in Text-to-SQL systems. |
| Outcome: | The proposed dataset contains 455 natural language/SQL-pairs over 35 big databases with varying level of complexity for English and German. |
Instructing Large Language Models to Identify and Ignore Irrelevant Conditions (2024.naacl-long)
Copied to clipboard
| Challenge: | Existing CoT prompting methods elicited multi-step reasoning abilities of large language models (LLMs) but they were seriously confused by the irrelevant conditions, resulting in low accuracy. |
| Approach: | They propose a method that instructs large language models to identify and ignore irrelevant conditions and prompts them to verify the irrelevant conditions. |
| Outcome: | The proposed approach outperforms existing methods on MWPs with GPT-3.5-Turbo and I3C-Select. |
“You Gotta be a Doctor, Lin” : An Investigation of Name-Based Bias of Large Language Models in Employment Recommendations (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have demonstrated racial and gender biases in various applications. |
| Approach: | They use Large Language Models to simulate hiring decisions and salary recommendations for candidates with 320 first names that strongly signal their race and gender, across over 750,000 prompts. |
| Outcome: | The proposed models favor candidates with White female-sounding names over other demographic groups across 40 occupations. |
Efficient Dynamic Clustering-Based Document Compression for Retrieval-Augmented-Generation (2025.findings-emnlp)
Copied to clipboard
| Challenge: | RAG implementations face challenges in addressing retrieved noise and redundant content . current RAG methods lack the ability to exploit fine-grained inter-document relationships . |
| Approach: | They propose a retrieval-augmented generation framework that exploits latent inter-document relationships while removing irrelevant information and redundant content. |
| Outcome: | The proposed framework achieves consistent performance improvements on knowledge-QA and hallucination-Detection datasets. |
Rationales for Answers to Simple Math Word Problems Confuse Large Language Models (2024.findings-acl)
Copied to clipboard
| Challenge: | Recent studies show that large language models have advanced mathematical problem-solving abilities in grade school math word problems. |
| Approach: | They propose to combine fine-tuning and prompt-based methods to improve performance . they propose to use a hybrid algorithm to fine- tune LLMs on specific tasks . |
| Outcome: | The proposed methods improve performance on the proposed reasoning process evaluation benchmarks. |
CAPE: Context-Aware Personality Evaluation Framework for Large Language Models (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing studies use a context-free approach to assess humans . existing studies use the Disney World test, which ignores real-world applications . |
| Approach: | They propose a framework to assess personality traits in large language models . they use conversational history to quantify the consistency of LLM responses . |
| Outcome: | The proposed framework improves consistency of responses in large language models . it also shows that conversational history enhances consistency and personality shifts . |
HydraRAG: Structured Cross-Source Enhanced Large Language Model Reasoning (2025.emnlp-main)
Copied to clipboard
| Challenge: | Current RAG system retrieves evidence from knowledge graphs and text documents but has limitations in multi-hop reasoning, multi-entity questions, and source verification. |
| Approach: | They propose a training-free framework that unifies graph topology, document semantics, and source reliability to support deep, faithful reasoning in large language models. |
| Outcome: | The proposed framework outperforms the current hybrid model-based model-driven system by 20.3% and 30.1% on seven benchmark datasets. |
GPT is Not an Annotator: The Necessity of Human Annotation in Fairness Benchmark Construction (2024.acl-long)
Copied to clipboard
| Challenge: | Current benchmarks for social biases have limitations in scope, grounding, quality and human effort required. |
| Approach: | They propose to use a language model to help with the development of bias benchmarks . they extend previous work to a new community and set of biases: the Jewish community and antisemitism . |
| Outcome: | The proposed LLM does not perform well on the Jewish community and antisemitism task. |
Decoding Stumpers: Large Language Models vs. Human Problem-Solvers (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Recent advances in large language models have led to the development of systems 2 models that can solve complex tasks and predict human behavior. |
| Approach: | They compare the performance of four state-of-the-art LLMs to human participants and compare their results to stumpers, a unique single-step intuition problem that humans can easily verify. |
| Outcome: | The proposed models excel in solving stumpers and surpass human performance on stumpers, while humans exhibit superior skills in verifying solutions to the same problems. |
AfriInstruct: Instruction Tuning of African Languages for Diverse Tasks (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models (LLMs) for African languages perform worse compared to high-resource languages. |
| Approach: | They propose a model that specializes in instruction-tuning of multiple African languages covering various tasks. |
| Outcome: | The proposed model outperforms GPT-3.5-Turbo and other models of similar size in multiple tasks. |
SWAG: Storytelling With Action Guidance (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models (LLMs) are used for one-shot creation, but they can produce inconsistent but not necessarily engaging content. |
| Approach: | They propose a novel approach to storytelling with large language models that reduces story writing to a search problem through a two-model feedback loop. |
| Outcome: | The proposed approach outperforms existing methods when evaluated by GPT-4 and through human evaluation. |
Chain of Condition: Construct, Verify and Solve Conditions for Conditional Question Answering (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for conditional question answering struggle with finding probable answers and identifying missing conditions. |
| Approach: | They propose a conditional question answering prompting approach that first identifies all conditions and constructs their logical relationships explicitly according to the document, then verifyes whether these conditions are satisfied and finally solves the logical expression to indicate any missing conditions. |
| Outcome: | The proposed method outperforms existing prompting baselines on two CQA benchmark datasets and can facilitate GPT-3.5-Turbo or GPT-4 to outperFORM all existing supervised models. |
MT-Eval: A Multi-Turn Capabilities Evaluation Benchmark for Large Language Models (2024.emnlp-main)
Copied to clipboard
Wai-Chung Kwan, Xingshan Zeng, Yuxin Jiang, Yufei Wang, Liangyou Li, Lifeng Shang, Xin Jiang, Qun Liu, Kam-Fai Wong
| Challenge: | Existing evaluation frameworks focus on single-turn evaluations, overlooking the models’ capabilities in multi-turn interactions. |
| Approach: | They propose a benchmark to evaluate the multi-turn conversational abilities of large language models (LLMs) by analyzing human-LLM conversations and constructing multi-turned queries for each category using GPT-4. |
| Outcome: | The proposed model outperforms open-source models in multi-turn tasks while retaining and recalling historical information. |
GRADA: Graph-based Reranking against Adversarial Documents Attack (2025.emnlp-main)
Copied to clipboard
Jingjie Zheng, Aryo Pradipta Gema, Giwon Hong, Xuanli He, Pasquale Minervini, Youcheng Sun, Qiongkai Xu
| Challenge: | Retrieval Augmented Generation (RAG) frameworks are susceptible to adversarial attacks that manipulate the retrieval process by introducing documents that are adversarially similar to the query. |
| Approach: | They propose a framework that integrates external retrieval modules into RAG frameworks to improve the factual accuracy of large language models. |
| Outcome: | The proposed framework reduces adversarial attacks by 80% while maintaining minimal loss in accuracy. |
Trojsten Benchmark: Evaluating LLM Problem-Solving in Slovak STEM Competition Problems (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large language models have been used for grading open-ended responses and providing feedback beyond traditional methods. |
| Approach: | They propose a Slovak-language dataset and a rubric-based LLM grading framework . they quantify multistep reasoning performance by difficulty and show consistency under difficult items . |
| Outcome: | The proposed model outperforms existing models on Slovak-language competition problems . the model shows consistent underperformance on harder items and language sensitivity . |