Papers with human alignment
SAJA: A Simple Approach to Judge Alignment for LLM-as-a-Judge (2026.acl-industry)
Copied to clipboard
| Challenge: | Current approaches to evaluate text at scale require multiple calls and per-dataset prompt tuning. |
| Approach: | They propose a model-agnostic approach to evaluate judge alignment that uses a lightweight calibration head. |
| Outcome: | a new model with SAJA matches more complex systems across four evaluation paradigms . it outperforms uncalibrated models on MT-Bench pairwise preference and competitive performance on five classification benchmarks compared to uncalibred models . |
Persona Prompting as a Lens on LLM Social Reasoning (2026.eacl-long)
Copied to clipboard
Jing Yang, Moritz Hechtbauer, Elisabeth Khalilov, Evelyn Luise Brinkmann, Vera Schmitt, Nils Feldhus
| Challenge: | Persona prompting (PP) is increasingly used to steer large language models towards user-specific generation, but its effect on rationales remains underexplored. |
| Approach: | They examine how LLM-generated rationales vary when conditioned on different demographic personas . they use word-level rationale annotations to measure agreement with human annotations based on PP . |
| Outcome: | The proposed model improves classification on the most subjective task, but fails to align with real-world demographic counterparts. |
Fairer Preferences Elicit Improved Human-Aligned Large Language Model Judgments (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) have shown promising abilities as cost-effective and reference-free evaluators for assessing language quality. |
| Approach: | They propose an automatic Zero-shot Evaluation-oriented Prompt Optimization framework which produces fairer preference decisions and improves human alignment. |
| Outcome: | The proposed framework produces fairer preference decisions and better aligns LLMs with humans. |
MM-BizRAG: Rethinking Multimodal Retrieval-Augmented Generation for General Purpose Enterprise Q&A (2026.acl-industry)
Copied to clipboard
Hanoz Bhathena, Parin Rajesh Jhaveri, Rohan Mittal, Prateek Singh, Aymen Kallala, Rachneet Kaur, Yiqiao Jin, Zhen Zeng, Adwait Ratnaparkhi, Denis Kochedykov
| Challenge: | Recent advances in multimodal retrieval-augmented generation (MM-RAG) have shifted toward minimal parsing, relying on page-level images for producing retriever embeddings and answer generation. |
| Approach: | They propose a document structure-aware split that extracts and represents document structure via a structure-based split that dynamically routes documents through orientation-specific ingestion pipelines. |
| Outcome: | The proposed model outperforms state-of-the-art vision-centric baselines by up to 32% points and achieves strong gains on report-style layouts. |
Generative Interpretation: Toward Human-Like Evaluation for Educational Question-Answer Pair Generation (2024.findings-eacl)
Copied to clipboard
| Challenge: | Existing evaluation methods often fail to produce objective results and favor high similarity to the ground-truth question-answer pairs. |
| Approach: | They propose an alternative approach to evaluate question-answer generation using Generative Interpretation (GI) GI outperforms existing evaluation methods in terms of human alignment . |
| Outcome: | The proposed approach outperforms existing evaluation methods in human alignment and shows comparable performance with GPT3.5, only with BART-large. |
Knowledge Verification to Nip Hallucination in the Bud (2024.emnlp-main)
Copied to clipboard
| Challenge: | Recent studies have shown that large language models generate responses that sound plausible but contradict factual knowledge, a phenomenon known as hallucination. |
| Approach: | They propose a novel approach to align large language models to evaluate knowledge boundaries based on external knowledge to reduce hallucinations . |
| Outcome: | The proposed approach reduces hallucinations across six benchmarks using foundation LLMs of varying backbones and scales. |
Beyond Static Evaluation: A Dynamic Approach to Assessing AI Assistants’ API Invocation Capabilities (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing evaluation methods for human-machine interactions are static and can be misleading. |
| Approach: | They propose to use a LLM-based user agent to assess an assistant's API call capability without human involvement. |
| Outcome: | The proposed method mirrors real human conversation patterns in human-machine interactions, and shows that it aligns more closely with human assessment. |
Calibrating LLM-Based Evaluator (2024.lrec-main)
Copied to clipboard
Yuxuan Liu, Tianchi Yang, Shaohan Huang, Zihan Zhang, Haizhen Huang, Furu Wei, Weiwei Deng, Feng Sun, Qi Zhang
| Challenge: | Existing models for large language models lack the ability to calibrate their outputs towards human preference. |
| Approach: | They propose a multi-stage, gradient-free approach to calibrate an LLM-based evaluator toward human preference. |
| Outcome: | The proposed approach improves correlation with expert evaluation on multiple text quality evaluation datasets. |
Can Large Language Models Capture Dissenting Human Voices? (2023.emnlp-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) have shown impressive achievements in solving a broad range of tasks. |
| Approach: | They evaluate the performance and alignment of large language models with humans using Monte Carlo Estimation and Log Probability Estimationic methods to estimate the multinomial distribution. |
| Outcome: | The proposed models fail to capture human disagreement distribution and inference and human alignment performance plunge even further on data samples with high disagreement levels raising concerns about their natural language understanding ability and representativeness to a larger human population. |
ExSum: From Local Explanations to Model Understanding (2022.naacl-main)
Copied to clipboard
| Challenge: | Interpretability methods are developed to understand the working mechanisms of black-box models. |
| Approach: | They propose a mathematical framework for quantifying model understanding with an explanation summary. |
| Outcome: | The proposed framework highlights limitations in the current practice and reveals easily overlooked properties of the model. |
A Practical Analysis of Human Alignment with *PO (2025.findings-naacl)
Copied to clipboard
| Challenge: | Prior research focused on identifying the best-performing method to varying hyperparameters . prior research focused primarily on a grid search, which can be impractical for general practitioners . |
| Approach: | They propose a preference optimization method that is more stable across hyperparameters and reduces the average response length. |
| Outcome: | The proposed method increases likelihood of achieving better results through various metrics, such as KL divergence and response length. |
CycleAlign: Iterative Distillation from Black-box LLM to White-box Models for Better Human Alignment (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing language models that generate harmful responses are constrained by their inherent capability. |
| Approach: | They propose to align large language models with human preferences from AI feedback. |
| Outcome: | The proposed framework improves the alignment of large language models with human preferences from AI feedback. |
Scaling Data Diversity for Fine-Tuning Language Models in Human Alignment (2024.lrec-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) can reveal toxic or offensive content inadvertently or intentionally. |
| Approach: | They propose to control the diversity of both sides according to the number of samples for fine-tuning, which can directly reflect their impact. |
| Outcome: | The proposed approach improves the performance of large language models after fine-tuning. |
Human-Centered Supervision for Sentiment Analysis in Telugu: A Systematic Inquiry Beyond Accuracy (2026.findings-acl)
Copied to clipboard
Vallabhaneni Raj Kumar, Ashwin S, Supriya Manna, Niladri Sett, Cheedella V S N M S Hema Harshitha, Kurakula Harshitha, Basina Deepakraj, Anand Kumar Sharma, Tanuj Sarkar, Samanthapudi Shakeer, Bondada Navaneeth Krishna
| Challenge: | a limited amount of annotated data has slowed progress in machine learning for low-resource languages . a sentiment label records an annotator's final decision, but it is not a valid record of the annotation's interpretation. |
| Approach: | They propose a large-scale Telugu sentiment classification dataset annotated with sentiment labels and human-selected rationales from multiple native speakers. |
| Outcome: | The proposed model improves classification performance, explanation quality, and social bias by incorporating human rationales. |
HumanLLM: Benchmarking and Improving LLM Anthropomorphism via Human Cognitive Patterns (2026.acl-long)
Copied to clipboard
Xintao Wang, Jian Yang, Weiyuan Li, Rui Xie, Jen-tse Huang, Jun Gao, Shuai Huang, Yueping Kang, Yuanli Guo, Hongwei Feng, Yanghua Xiao
| Challenge: | Large Language Models (LLMs) have demonstrated remarkable capabilities in reasoning and generation, serving as the foundation for advanced persona simulation and Role-Playing Language Agents (RPLAs). |
| Approach: | They propose a framework that treats psychological patterns as interacting causal forces and synthesizes 113 scenarios where 2-5 patterns reinforce, conflict, or modulate each other. |
| Outcome: | The proposed framework outperforms Qwen3-32B on multi-pattern dynamics despite 4 fewer parameters. |