Research at Algoverse

Learn about our mission, explore our acclaimed conference publications, and delve into past student research papers.

Shared Parameter Subspaces and Cross-Task Linearity in Emergently Misaligned Behaviour

Authors: Daniel Aarao Reis Arturi, Eric Zhang, Andrew Adrian Ansah

Scratchpad Thinking: Alternation Between Storage and Computation in Latent Reasoning Models

Authors: Sayam Goyal, Brad Peters, María Emilia Granda, Akshath Vijayakumar Narmadha, Dharunish Yugeswardeenoo

WOLF: Werewolf-based Observations for LLM Deception and Falsehoods

Authors: Mrinal Agarwal, Saad Rana, Theo Sundoro, Hermela Berhe

AgentChangeBench: A Multi-Dimensional Evaluation Framework for Goal-Shift Robustness in Conversational AI

Authors: Manik Rana, Calissa Man, Jeffrey Paine, Anotida Expected Msiiwa

Chopping Trees: Semantic Similarity Based Dynamic Pruning for Tree-of-Thought Reasoning

Authors: Xirui Huang, Joongho Kim

A Few Bad Neurons: Isolating and Surgically Correcting Sycophancy

Authors: Claire O'Brien, Jessica Seto, Dristi Roy, Aditya Dwivedi

Amortized Latent Steering: Low-Cost Alternative to Test-Time Optimization

Authors: Nathan Egbuna, Saatvik Gaur

Automated Generation of Multilingual Jailbreak Prompts

Authors: Jonathan Ding, Khanak Jain, Dhruv Nair

Cross-Lingual Multimodal Retrieval-Augmented Generation for Open Question Answering in Tamil and Yoruba

Authors: Mobareji Abejide, Arya Ram

DuoLens: A Framework for Robust Detection of Machine-Generated Multilingual Text and Code

Authors: Shriyansh Agrawal, Aidan Lau, Sanyam Shah

Enhancing Rural Autonomous Driving Performance with Diffusion-Augmented Synthetic Datasets

Authors: Siddharth Arun, Trisha Panchangmath, Saanvi Celamkoti, Vayden Wong

ERGO: Entropy-guided Resetting for Generation Optimization in Multi-turn Language Models

Authors: Haziq Mohammad Khalid, Athikash Jeyaganthan, Timothy Do

Examining the Vulnerability of Multi-Agent Medical Systems to Human Interventions for Clinical Reasoning

Authors: Dillon Mehta, Rishi Malhotra, Adam Zobian, Yong Ying Tan, Samir Chopra, Daniella Rand, Natalie Pang, Abhiram Gudimella, Raghav Thallapragada, Derek Jiu

GUARD: Guiding Unbiased Alignment through Reward Debiasing

Authors: Advay Samnerkar, Doelle Bhattacharya

LSMAS (LLM Security Modeling via Activation Steering)

Authors: Anthony Kuang, Ahmed Ismail

Modeling and Predicting Multi-Turn Answer Instability in Large Language Models

Authors: Jiahang He, Rishi Ramachandran, Neel Ramachandran, Aryan Katakam

Multi-Turn LLM Systems for Diagnostic Decision-Making: Considerations, Biases, and Challenges

Authors: Sejong Kim, Drona Thoka, Varun Puttagunta, Kaylin Sheng, Mark Li, Adnan Ahmed, THI UYEN HANH LE, Sai Chidvilas Gudiboina, Ali Ugur

Novel Finetuning Strategies for Adapting Biomedical Vision Language Models to Organ-Centered Pathology Microscopy Tasks

Authors: Siddharth Venkatesh, Ayman Sheikh, Anne Essien Essien, Pratibh, Rayhan Roswendi, Jeremiah Zhang

Probe-Rewrite-Evaluate: A Workflow for Reliable Benchmarks and Quantifying Evaluation Awareness

Authors: Lang Xiong, Nishant Bhargava, Jeremy Chang, Jianhang Hong

Prompting Toxicity: Analyzing Biosafety Risks in Genomic Language Models

Authors: Akshay Murthy, Mengmeng Zhang, Shanmukhi Kannamangalam

Scratchpad Thinking: Alternation Between Storage and Computation in Latent Reasoning Models

Authors: Sayam Goyal, Brad Peters, María Emilia Granda, Akshath Vijayakumar Narmadha, dharunish yugeswardeenoo

SMAGDi: Socratic Multi Agent Interaction Graph Distillation for Efficient High Accuracy Reasoning

Authors: Aayush Aluru, Myra N. Malik, Samarth Patankar

StealthEval: A Probe-Rewrite-Evaluate Workflow for Reliable Benchmarks

Authors: Lang Xiong, Nishant Bhargava, Jeremy Chang, Jianhang Hong

SwiftSolve: A Self-Iterative, Complexity-Aware Multi-Agent Framework for Competitive Programming

Authors: Adhyayan Veer Singh, Aaron Shen, Brian Law, Ahmed Ismail

User Confidence-Fueled Stereotypes: Investigating Sycophantic Amplification of Implicit Bias in Language Models

Authors: Hannah You, Daniel Wang, Victor Chan, Mirabel Wang

Weight- and Activation-Based Steering Methods Provide Complementary Control of Biochemical Traits in Protein Language Models

Authors: Armaity Katki, Nathan Choi, Son Sophak Otra

Amortized Latent Steering: Low-Cost Alternative to Test-Time Optimization

Authors: Nathan Egbuna, Saatvik Gaur

ERGO: Entropy-guided Resetting for Generation Optimization in Multi-turn Language Models

Authors: Haziq Mohammad Khalid, Athikash Jeyaganthan, Timothy Do

LSMAS (LLM Security Modeling via Activation Steering)

Authors: Anthony Kuang, Ahmed Ismail

Modeling and Predicting Multi-Turn Answer Instability in Large Language Models

Authors: Jiahang He, Rishi Ramachandran, Neel Ramachandran, Aryan Katakam

Multi-Turn LLM Systems for Diagnostic Decision-Making: Considerations, Biases, and Challenges

Authors: Sejong Kim, Drona Thoka, Varun Puttagunta, Kaylin Sheng, Mark Li, Adnan Ahmed, THI UYEN HANH LE, Sai Chidvilas Gudiboina, Ali Ugur

Novel Finetuning Strategies for Adapting Biomedical Vision Language Models to Organ-Centered Pathology Microscopy Tasks

Authors: Siddharth Venkatesh, Ayman Sheikh, Anne Essien Essien, Pratibh, Rayhan Roswendi, Jeremiah Zhang

Probe-Rewrite-Evaluate: A Workflow for Reliable Benchmarks and Quantifying Evaluation Awareness

Authors: Lang Xiong, Nishant Bhargava, Jeremy Chang, Jianhang Hong

Prompting Toxicity: Analyzing Biosafety Risks in Genomic Language Models

Authors: Akshay Murthy, Mengmeng Zhang, Shanmukhi Kannamangalam

SMAGDi: Socratic Multi Agent Interaction Graph Distillation for Efficient High Accuracy Reasoning

Authors: Aayush Aluru, Myra N. Malik, Samarth Patankar

SwiftSolve: A Self-Iterative, Complexity-Aware Multi-Agent Framework for Competitive Programming

Authors: Adhyayan Veer Singh, Aaron Shen, Brian Law, Ahmed Ismail

User Confidence-Fueled Stereotypes: Investigating Sycophantic Amplification of Implicit Bias in Language Models

Authors: Hannah You, Daniel Wang, Victor Chan, Mirabel Wang

Weight- and Activation-Based Steering Methods Provide Complementary Control of Biochemical Traits in Protein Language Models

Authors: Armaity Katki, Nathan Choi, Son Sophak Otra

Amortized Latent Steering: Low-Cost Alternative to Test-Time Optimization

Authors: Nathan Egbuna, Saatvik Gaur

Grounding Foundational Vision Models with 3D Human Poses for Robust Action Recognition

Authors: Nicholas Babey, Tiffany Gu, Yiheng Li

MISCHIEF: A Benchmark in Minimal-Pairs of Safety and Culture for Holistic Evaluation of Fine-Grained Image-Caption Alignment

Authors: Sagarika Banerjee, Tangatar Madi, Advait Swaminathan, Nguyen Dao Manh Anh

Universal Neurons in GPT-2: Emergence, Persistence, and Functional Impact

Authors: Advey Nandan, Cheng-Ting Chou, Amrit Kurakula

What Do Refusal Tokens Learn? Fine-Grained Representations and Evidence for Downstream Steering

Authors: Rishab Alagharu, Ishneet Sukhvinder Singh, Anjali Batta, Jaelyn S. Liang, Shaibi Shamsudeen, Arnav Sheth

When Less is More: 8-bit Quantization Improves Continual Learning in Large Language Models

Authors: Michael Shihong Zhang, Rishi Adi Ruia, Arnav Kewalram, Saathvik Dharmapuram

A Few Bad Neurons: Isolating and Surgically Correcting Sycophancy

Authors: Claire O'Brien, Jessica Seto, Dristi Roy, Aditya Dwivedi

Active Inference Control: Steering, Not Just Scaling, Language Model Reasoning

Authors: Josh Karthikeyan, Kai Fu, Derek Jiu

Adaptive Originality Filtering: Rejection-Based Prompting and RiddleScore for Culturally Grounded Multilingual Riddle Generation

Authors: Duy Le, Kent Ziti, Evan Girard-Sun

Adversarial Behavior in Research Settings: Conducting Control Evaluations with RE-Bench

Authors: Harini Rajakumar, Vanessa Nwauwa

ASCII-Bench: Evaluating Language-Model-Based Understanding of Visually-Oriented Text

Authors: Kerry Luo, Joshua Peguero, Anvay Patil, Megan Van Overborg, Ryan Sarmiento

Automated Specialization of Stateful Agent Systems

Authors: Myan Vu, Harrish Ayyanar, Pang Jiang, Anwiketh Reddy

Cognitive Behavior Modeling via Activation Steering (CBMAS)

Authors: Anthony Kuang, Ayo Akinkugbe, Ahmed Ismail

Confidence-Coverage Gating for Early Exit

Authors: Aaroosh Rustagi, Hsien Xin Peng, Khushal Murthy, Attrey Koul

Cross-Lingual Multimodal Retrieval-Augmented Generation for Open Question Answering in Tamil and Yoruba

Authors: Kiran Raja, Mobareji Abejide, Arya Ram, Benjamin Liu

Death by a Thousand Directions: Exploring the Geometry of Harmfulness in LLMs through Subconcept Probing

Authors: Saleena Angeline Sartawita, McNair Shah, Adhitya Rajendra Kumar, Naitik Chheda

DecepBench: Benchmarking Multimodal Deception Detection

Authors: Vittesh Maganti, Nysa Lalye, Ethan Braverman

Discovering Transformer Circuits via a Hybrid Attribution and Pruning Framework

Authors: Hao Gu, Vibhas Nair, Amrithaa Ashok Kumar

Don't Think of the White Bear: Ironic Negation in Transformer Models under Cognitive Load

Authors: Logan Mann, Sarah Tandon, Chenhao Sun, Savar Toteja

Emotional Framing as a Control Channel: Effects of Prompt Valence on LLM Performance

Authors: Enmanuel Felix-Pena, Tiki Li, Ayo Akinkugbe, Wayne Chen, Ethan Hin

Examining the Vulnerability of Multi-Agent Medical Systems to Human Interventions for Clinical Reasoning

Authors: Benjamin Liu, Dillon Mehta, Rishi Malhotra, Adam Zobian, Yong Ying Tan, Samir Chopra, Daniella Rand, Natalie Pang, Abhiram Gudimella, Raghav Thallapragada, Derek Jiu, Prisha Shah

Extending AutoCompressors via Surprisal-Based Dynamic Segmentation

Authors: Srivishnu Ramamurthi, Richard Xu, Raine Ma, Dawson Park, David Guo

FRIT: Using Causal Importance to Improve Chain-of-Thought Faithfulness

Authors: Anand Swaroop, Akshat Nallani, Saksham Uboweja, Adiliia Uzdenova, Michael Nguyen

GASLIGHTBENCH: Quantifying LLM Susceptibility to Social Prompting

Authors: Lening Nick Cui, Sahil Ghosh, Gareth Lee, Xuanzhe Yao, Swarit Srivastava, William H. Logian, Michael Li, Ellie Podoshev

GUARD: Guiding Unbiased Alignment through Reward Debiasing

Authors: Advay Samnerkar, Doelle Bhattacharya, Kailash Ranganathan

Idea: Fairness Constraints as Reliability Guarantees for RLHF Reward Models

Authors: Advay Samnerkar, Doelle Bhattacharya, Kailash Ranganathan

Inference-Time Chain-of-Thought Pruning with Latent Informativeness Signals

Authors: Sophie Li, Nicholas Huang, Nina Luo, Vincent Lin

LoRA-Guided PPO for Cost-Aware and Compute-Efficient Agent Orchestration

Authors: Aneesh Durai, Joshua Cong Hu, Kevaan Buch

Mechanistic Interpretability of Semantic Abstraction in Biomedical Texts

Authors: Nikhil Gourisetty, Snata Mohanty, Vishnu Srinivas, Soumil Jain, Sunith Vallabhaneni

Mitigating Sycophancy in Language Models via Sparse Activation Fusion and Multi-Layer Activation Steering

Authors: Pyae Phoo Min, Avigya Paudel, Naufal Adityo, Arthur Zhu, Andrew Rufail

Multi-Turn LLM Systems for Diagnostic Decision-Making: Considerations, Biases, and Challenges

Authors: Benjamin Liu, Sejong Kim, Drona Thoka, Varun Puttagunta, Kaylin Sheng, Mark Li, Adnan Ahmed, Thi Uyen Hanh Le, Sai Chidvilas Gudiboina, Ali Ugur

Peek-a-Boo Reasoning: Contrastive Region Masking in MLLMs

Authors: Anjana Nair, Yushen Li, Adhitya Rajendra Kumar

Predicting Emergent Software Engineering Capabilities by Fine-tuning

Authors: Jason Jiyachon, Terry Huang, Henry Velasquez

Probe-Rewrite-Evaluate: A Workflow for Reliable Benchmarks and Quantifying Evaluation Awareness

Authors: Lang Xiong, Nishant Bhargava, Jeremy Chang, Jianhang Hong

Sarc7: Evaluating Sarcasm Detection and Generation with Seven Types and Emotion-Informed Techniques

Authors: Lang Xiong, Raina Gao, Alyssa Jeong

Translation Bias and Accuracy in Multilingual LLMs for Cross-Language Claim Verification

Authors: Aryan Singhal, Veronica Shao, Gary Sun, Ryan Ding

QIANets for Reduced Latency and Improved Inference Times in CNN Models

Authors: Zhumazhan Balapanov, Edward Magongo, Vanessa Matvei, Olivia Holmberg

Semantic Self-Consistency: Enhancing Language Model Reasoning via Semantic Weighting

Authors: Tim Knappe, Ryan Li, Ayush Chauhan, Kaylee Chhua

Fine-Tuning Language Models for Ethical Ambiguity

Authors: Pranav Senthilkumar, Visshwa Bala, Prisha Jain, Aneesa Maity

NusaMT-7B: Machine Translation for Low-Resource Indonesian Languages with LLMs

Author: William Tan

DiversityMedQA: Assessing Demographic Biases in Medical Diagnosis using LLMs

Authors: Rajat Rawat, Hudson McBride, Rajarshi Ghosh, Dhiyaan Nirmal, Jong Moon, Dhruv Alamuri

AAVENUE: Detecting LLM Biases on NLU Tasks in AAVE via a Novel Benchmark

Authors: Abhay Gupta, Philip Meng, Ece Yurtseven