Mohit Bansal
@mohitbansal.bsky.social
Parker Distinguished Professor, @UNC. Program Chair #EMNLP2024. Director http://MURGeLab.cs.unc.edu (@uncnlp). @Berkeley_AI @TTIC_Connect @IITKanpur
#NLP #CV #AI #ML
https://www.cs.unc.edu/~mbansal/
#NLP #CV #AI #ML
https://www.cs.unc.edu/~mbansal/
Pinned
Mohit Bansal
@mohitbansal.bsky.social
· Jan 21
🎉Congratulations to Prof. @mohitbansal.bsky.social on being named a 2025 @RealAAAI Fellow for "significant contributions to multimodal AI foundations & faithful language generation and summarization." 👏
16 Fellows chosen worldwide by cmte. of 9 past fellows & ex-president: aaai.org/about-aaai/a...
16 Fellows chosen worldwide by cmte. of 9 past fellows & ex-president: aaai.org/about-aaai/a...
Thanks @AAAI for selecting me as a #AAAI Fellow! Very humbled+excited to be a part of the respected cohort of this+past years' fellows (& congrats everyone)! 🙏
100% credit goes to my amazing past/current students+postdocs+collab for their work (& thanks to mentors+family)!💙
aaai.org/about-aaai/a...
100% credit goes to my amazing past/current students+postdocs+collab for their work (& thanks to mentors+family)!💙
aaai.org/about-aaai/a...
Reposted by Mohit Bansal
Overdue job update — I am now:
- A Visiting Scientist at @schmidtsciences.bsky.social, supporting AI safety & interpretability
- A Visiting Researcher at Stanford NLP Group, working with @cgpotts.bsky.social
So grateful to keep working in this fascinating area—and to start supporting others too :)
- A Visiting Scientist at @schmidtsciences.bsky.social, supporting AI safety & interpretability
- A Visiting Researcher at Stanford NLP Group, working with @cgpotts.bsky.social
So grateful to keep working in this fascinating area—and to start supporting others too :)
July 14, 2025 at 5:06 PM
Overdue job update — I am now:
- A Visiting Scientist at @schmidtsciences.bsky.social, supporting AI safety & interpretability
- A Visiting Researcher at Stanford NLP Group, working with @cgpotts.bsky.social
So grateful to keep working in this fascinating area—and to start supporting others too :)
- A Visiting Scientist at @schmidtsciences.bsky.social, supporting AI safety & interpretability
- A Visiting Researcher at Stanford NLP Group, working with @cgpotts.bsky.social
So grateful to keep working in this fascinating area—and to start supporting others too :)
Reposted by Mohit Bansal
📢 Speakers Announcement #AthNLP2025
We’re thrilled to welcome a new lineup of brilliant minds to the ATHNLP stage!🚀
Meet our new NLP speakers shaping the future.
📅 Dates: 4-10 September 2025 athnlp.github.io/2025/speaker...
#ATHNLP #NLP #AI #MachineLearning #Athens
We’re thrilled to welcome a new lineup of brilliant minds to the ATHNLP stage!🚀
Meet our new NLP speakers shaping the future.
📅 Dates: 4-10 September 2025 athnlp.github.io/2025/speaker...
#ATHNLP #NLP #AI #MachineLearning #Athens
June 27, 2025 at 2:49 PM
📢 Speakers Announcement #AthNLP2025
We’re thrilled to welcome a new lineup of brilliant minds to the ATHNLP stage!🚀
Meet our new NLP speakers shaping the future.
📅 Dates: 4-10 September 2025 athnlp.github.io/2025/speaker...
#ATHNLP #NLP #AI #MachineLearning #Athens
We’re thrilled to welcome a new lineup of brilliant minds to the ATHNLP stage!🚀
Meet our new NLP speakers shaping the future.
📅 Dates: 4-10 September 2025 athnlp.github.io/2025/speaker...
#ATHNLP #NLP #AI #MachineLearning #Athens
Reposted by Mohit Bansal
Looking forward to this year's edition! With great speakers: Ryan McDonald Yulan He @vn-ml.bsky.social @antonisa.bsky.social Raquel Fernandez @annarogers.bsky.social Preslav Nakov @mohitbansal.bsky.social @eunsol.bsky.social Marie-Catherine de Marnefffe !
📢 10 Days Left to apply for the AthNLP - Athens Natural Language Processing Summer School!
✍ Get your applications in before June 15th!
athnlp.github.io/2025/cfp.html
✍ Get your applications in before June 15th!
athnlp.github.io/2025/cfp.html
June 6, 2025 at 9:10 AM
Looking forward to this year's edition! With great speakers: Ryan McDonald Yulan He @vn-ml.bsky.social @antonisa.bsky.social Raquel Fernandez @annarogers.bsky.social Preslav Nakov @mohitbansal.bsky.social @eunsol.bsky.social Marie-Catherine de Marnefffe !
🔥 Huge CONGRATS to Jaemin + @jhucompsci.bsky.social! 🎉
Very proud of his journey as an amazing researcher (covering groundbreaking, foundational research on important aspects of multimodality+other areas) & as an awesome, selfless mentor/teamplayer 💙
-- Apply to his group & grab him for gap year!
Very proud of his journey as an amazing researcher (covering groundbreaking, foundational research on important aspects of multimodality+other areas) & as an awesome, selfless mentor/teamplayer 💙
-- Apply to his group & grab him for gap year!
Some personal updates:
- I've completed my PhD at @unccs.bsky.social! 🎓
- Starting Fall 2026, I'll be joining the CS dept. at Johns Hopkins University @jhucompsci.bsky.social as an Assistant Professor 💙
- Currently exploring options for my gap year (Aug 2025 - Jul 2026), so feel free to reach out! 🔎
- I've completed my PhD at @unccs.bsky.social! 🎓
- Starting Fall 2026, I'll be joining the CS dept. at Johns Hopkins University @jhucompsci.bsky.social as an Assistant Professor 💙
- Currently exploring options for my gap year (Aug 2025 - Jul 2026), so feel free to reach out! 🔎
May 20, 2025 at 6:18 PM
🔥 Huge CONGRATS to Jaemin + @jhucompsci.bsky.social! 🎉
Very proud of his journey as an amazing researcher (covering groundbreaking, foundational research on important aspects of multimodality+other areas) & as an awesome, selfless mentor/teamplayer 💙
-- Apply to his group & grab him for gap year!
Very proud of his journey as an amazing researcher (covering groundbreaking, foundational research on important aspects of multimodality+other areas) & as an awesome, selfless mentor/teamplayer 💙
-- Apply to his group & grab him for gap year!
Reposted by Mohit Bansal
🚨 Introducing our @tmlrorg.bsky.social paper “Unlearning Sensitive Information in Multimodal LLMs: Benchmark and Attack-Defense Evaluation”
We present UnLOK-VQA, a benchmark to evaluate unlearning in vision-and-language models, where both images and text may encode sensitive or private information.
We present UnLOK-VQA, a benchmark to evaluate unlearning in vision-and-language models, where both images and text may encode sensitive or private information.
May 7, 2025 at 6:55 PM
🚨 Introducing our @tmlrorg.bsky.social paper “Unlearning Sensitive Information in Multimodal LLMs: Benchmark and Attack-Defense Evaluation”
We present UnLOK-VQA, a benchmark to evaluate unlearning in vision-and-language models, where both images and text may encode sensitive or private information.
We present UnLOK-VQA, a benchmark to evaluate unlearning in vision-and-language models, where both images and text may encode sensitive or private information.
🔥 BIG CONGRATS to Elias (and UT Austin)! Really proud of you -- it has been a complete pleasure to work with Elias and see him grow into a strong PI on *all* axes 🤗
Make sure to apply for your PhD with him -- he is an amazing advisor and person! 💙
Make sure to apply for your PhD with him -- he is an amazing advisor and person! 💙
Extremely excited to announce that I will be joining
@utaustin.bsky.social Computer Science in August 2025 as an Assistant Professor! 🎉
@utaustin.bsky.social Computer Science in August 2025 as an Assistant Professor! 🎉
May 5, 2025 at 10:00 PM
🔥 BIG CONGRATS to Elias (and UT Austin)! Really proud of you -- it has been a complete pleasure to work with Elias and see him grow into a strong PI on *all* axes 🤗
Make sure to apply for your PhD with him -- he is an amazing advisor and person! 💙
Make sure to apply for your PhD with him -- he is an amazing advisor and person! 💙
Reposted by Mohit Bansal
🌵 I'm going to be presenting PBT at #NAACL2025 today at 2PM! Come by poster session 2 if you want to hear about:
-- balancing positive and negative persuasion
-- improving LLM teamwork/debate
-- training models on simulated dialogues
With @mohitbansal.bsky.social and @peterbhase.bsky.social
-- balancing positive and negative persuasion
-- improving LLM teamwork/debate
-- training models on simulated dialogues
With @mohitbansal.bsky.social and @peterbhase.bsky.social
🎉Very excited that our work on Persuasion-Balanced Training has been accepted to #NAACL2025! We introduce a multi-agent tree-based method for teaching models to balance:
1️⃣ Accepting persuasion when it helps
2️⃣ Resisting persuasion when it hurts (e.g. misinformation)
arxiv.org/abs/2410.14596
🧵 1/4
1️⃣ Accepting persuasion when it helps
2️⃣ Resisting persuasion when it hurts (e.g. misinformation)
arxiv.org/abs/2410.14596
🧵 1/4
April 30, 2025 at 3:04 PM
🌵 I'm going to be presenting PBT at #NAACL2025 today at 2PM! Come by poster session 2 if you want to hear about:
-- balancing positive and negative persuasion
-- improving LLM teamwork/debate
-- training models on simulated dialogues
With @mohitbansal.bsky.social and @peterbhase.bsky.social
-- balancing positive and negative persuasion
-- improving LLM teamwork/debate
-- training models on simulated dialogues
With @mohitbansal.bsky.social and @peterbhase.bsky.social
Reposted by Mohit Bansal
I will be presenting ✨Reverse Thinking Makes LLMs Stronger Reasoners✨at #NAACL2025!
In this work, we show
- Improvements across 12 datasets
- Outperforms SFT with 10x more data
- Strong generalization to OOD datasets
📅4/30 2:00-3:30 Hall 3
Let's chat about LLM reasoning and its future directions!
In this work, we show
- Improvements across 12 datasets
- Outperforms SFT with 10x more data
- Strong generalization to OOD datasets
📅4/30 2:00-3:30 Hall 3
Let's chat about LLM reasoning and its future directions!
🚨 Reverse Thinking Makes LLMs Stronger Reasoners
We can often reason from a problem to a solution and also in reverse to enhance our overall reasoning. RevThink shows that LLMs can also benefit from reverse thinking 👉 13.53% gains + sample efficiency + strong generalization (on 4 OOD datasets)!
We can often reason from a problem to a solution and also in reverse to enhance our overall reasoning. RevThink shows that LLMs can also benefit from reverse thinking 👉 13.53% gains + sample efficiency + strong generalization (on 4 OOD datasets)!
April 29, 2025 at 11:21 PM
I will be presenting ✨Reverse Thinking Makes LLMs Stronger Reasoners✨at #NAACL2025!
In this work, we show
- Improvements across 12 datasets
- Outperforms SFT with 10x more data
- Strong generalization to OOD datasets
📅4/30 2:00-3:30 Hall 3
Let's chat about LLM reasoning and its future directions!
In this work, we show
- Improvements across 12 datasets
- Outperforms SFT with 10x more data
- Strong generalization to OOD datasets
📅4/30 2:00-3:30 Hall 3
Let's chat about LLM reasoning and its future directions!
Reposted by Mohit Bansal
✈️ Heading to #NAACL2025 to present 3 main conf. papers, covering training LLMs to balance accepting and rejecting persuasion, multi-agent refinement for more faithful generation, and adaptively addressing varying knowledge conflict.
Reach out if you want to chat!
Reach out if you want to chat!
April 29, 2025 at 5:52 PM
✈️ Heading to #NAACL2025 to present 3 main conf. papers, covering training LLMs to balance accepting and rejecting persuasion, multi-agent refinement for more faithful generation, and adaptively addressing varying knowledge conflict.
Reach out if you want to chat!
Reach out if you want to chat!
Reposted by Mohit Bansal
Check out 🚨CAPTURe🚨 -- a new benchmark testing spatial reasoning by making VLMs count objects under occlusion.
SOTA VLMs (GPT-4o, Qwen2-VL, Intern-VL2) have high error rates on CAPTURe (but humans have low error ✅) and models struggle to reason about occluded objects.
arxiv.org/abs/2504.15485
🧵👇
SOTA VLMs (GPT-4o, Qwen2-VL, Intern-VL2) have high error rates on CAPTURe (but humans have low error ✅) and models struggle to reason about occluded objects.
arxiv.org/abs/2504.15485
🧵👇
April 24, 2025 at 3:14 PM
Check out 🚨CAPTURe🚨 -- a new benchmark testing spatial reasoning by making VLMs count objects under occlusion.
SOTA VLMs (GPT-4o, Qwen2-VL, Intern-VL2) have high error rates on CAPTURe (but humans have low error ✅) and models struggle to reason about occluded objects.
arxiv.org/abs/2504.15485
🧵👇
SOTA VLMs (GPT-4o, Qwen2-VL, Intern-VL2) have high error rates on CAPTURe (but humans have low error ✅) and models struggle to reason about occluded objects.
arxiv.org/abs/2504.15485
🧵👇
In Singapore for #ICLR2025 this week to present papers + keynotes 👇, and looking forward to seeing everyone -- happy to chat about research, or faculty+postdoc+phd positions, or simply hanging out (feel free to ping)! 🙂
Also meet our awesome students/postdocs/collaborators presenting their work.
Also meet our awesome students/postdocs/collaborators presenting their work.
April 21, 2025 at 4:50 PM
In Singapore for #ICLR2025 this week to present papers + keynotes 👇, and looking forward to seeing everyone -- happy to chat about research, or faculty+postdoc+phd positions, or simply hanging out (feel free to ping)! 🙂
Also meet our awesome students/postdocs/collaborators presenting their work.
Also meet our awesome students/postdocs/collaborators presenting their work.
Reposted by Mohit Bansal
🚨Real-world retrieval is messy: queries are ambiguous or docs conflict & have incorrect/irrelevant info. How can we jointly address these problems?
➡️RAMDocs: challenging dataset w/ ambiguity, misinformation & noise
➡️MADAM-RAG: multi-agent framework, debates & aggregates evidence across sources
🧵⬇️
➡️RAMDocs: challenging dataset w/ ambiguity, misinformation & noise
➡️MADAM-RAG: multi-agent framework, debates & aggregates evidence across sources
🧵⬇️
April 18, 2025 at 5:06 PM
🚨Real-world retrieval is messy: queries are ambiguous or docs conflict & have incorrect/irrelevant info. How can we jointly address these problems?
➡️RAMDocs: challenging dataset w/ ambiguity, misinformation & noise
➡️MADAM-RAG: multi-agent framework, debates & aggregates evidence across sources
🧵⬇️
➡️RAMDocs: challenging dataset w/ ambiguity, misinformation & noise
➡️MADAM-RAG: multi-agent framework, debates & aggregates evidence across sources
🧵⬇️
Reposted by Mohit Bansal
Excited to share my first paper as first author: "Task-Circuit Quantization" 🎉
I led this work to explore how interpretability insights can drive smarter model compression. Big thank you to @esteng.bsky.social, Yi-Lin Sung, and @mohitbansal.bsky.social for mentorship and collaboration. More to come
I led this work to explore how interpretability insights can drive smarter model compression. Big thank you to @esteng.bsky.social, Yi-Lin Sung, and @mohitbansal.bsky.social for mentorship and collaboration. More to come
🚨Announcing TaCQ 🚨 a new mixed-precision quantization method that identifies critical weights to preserve. We integrate key ideas from circuit discovery, model editing, and input attribution to improve low-bit quant., w/ 96% 16-bit acc. at 3.1 avg bits (~6x compression)
📃 arxiv.org/abs/2504.07389
📃 arxiv.org/abs/2504.07389
April 16, 2025 at 4:19 PM
Excited to share my first paper as first author: "Task-Circuit Quantization" 🎉
I led this work to explore how interpretability insights can drive smarter model compression. Big thank you to @esteng.bsky.social, Yi-Lin Sung, and @mohitbansal.bsky.social for mentorship and collaboration. More to come
I led this work to explore how interpretability insights can drive smarter model compression. Big thank you to @esteng.bsky.social, Yi-Lin Sung, and @mohitbansal.bsky.social for mentorship and collaboration. More to come
Reposted by Mohit Bansal
What if we could transform advanced math problems into abstract programs that can generate endless, verifiable problem variants?
Presenting EFAGen, which automatically transforms static advanced math problems into their corresponding executable functional abstractions (EFAs).
🧵👇
Presenting EFAGen, which automatically transforms static advanced math problems into their corresponding executable functional abstractions (EFAs).
🧵👇
April 15, 2025 at 7:37 PM
What if we could transform advanced math problems into abstract programs that can generate endless, verifiable problem variants?
Presenting EFAGen, which automatically transforms static advanced math problems into their corresponding executable functional abstractions (EFAs).
🧵👇
Presenting EFAGen, which automatically transforms static advanced math problems into their corresponding executable functional abstractions (EFAs).
🧵👇
Reposted by Mohit Bansal
🚨Announcing TaCQ 🚨 a new mixed-precision quantization method that identifies critical weights to preserve. We integrate key ideas from circuit discovery, model editing, and input attribution to improve low-bit quant., w/ 96% 16-bit acc. at 3.1 avg bits (~6x compression)
📃 arxiv.org/abs/2504.07389
📃 arxiv.org/abs/2504.07389
April 12, 2025 at 2:19 PM
🚨Announcing TaCQ 🚨 a new mixed-precision quantization method that identifies critical weights to preserve. We integrate key ideas from circuit discovery, model editing, and input attribution to improve low-bit quant., w/ 96% 16-bit acc. at 3.1 avg bits (~6x compression)
📃 arxiv.org/abs/2504.07389
📃 arxiv.org/abs/2504.07389
Reposted by Mohit Bansal
🚨Exciting @icmlconf.bsky.social workshop alert 🚨
We’re thrilled to announce the #ICML2025 Workshop on Machine Unlearning for Generative AI (MUGen)!
⚡Join us in Vancouver this July to dive into cutting-edge research on unlearning in generative AI with top speakers and panelists! ⚡
We’re thrilled to announce the #ICML2025 Workshop on Machine Unlearning for Generative AI (MUGen)!
⚡Join us in Vancouver this July to dive into cutting-edge research on unlearning in generative AI with top speakers and panelists! ⚡
April 2, 2025 at 3:59 PM
🚨Exciting @icmlconf.bsky.social workshop alert 🚨
We’re thrilled to announce the #ICML2025 Workshop on Machine Unlearning for Generative AI (MUGen)!
⚡Join us in Vancouver this July to dive into cutting-edge research on unlearning in generative AI with top speakers and panelists! ⚡
We’re thrilled to announce the #ICML2025 Workshop on Machine Unlearning for Generative AI (MUGen)!
⚡Join us in Vancouver this July to dive into cutting-edge research on unlearning in generative AI with top speakers and panelists! ⚡
🎉🎉 Big congrats to @archiki.bsky.social on being awarded the @Apple AI/ML PhD Fellowship, for her extensive contributions in evaluating+improving reasoning in language/reward models and their applications to new domains (ReCEval, RepARe, System-1.x, ADaPT, ReGAL, ScPO, UTGen, GrIPS)! #ProudAdvisor
🥳🥳 Honored and grateful to be awarded the 2025 Apple Scholars in AI/ML PhD Fellowship! ✨
Huge shoutout to my advisor @mohitbansal.bsky.social, & many thanks to my lab mates @unccs.bsky.social , past collaborators + internship advisors for their support ☺️🙏
machinelearning.apple.com/updates/appl...
Huge shoutout to my advisor @mohitbansal.bsky.social, & many thanks to my lab mates @unccs.bsky.social , past collaborators + internship advisors for their support ☺️🙏
machinelearning.apple.com/updates/appl...
March 27, 2025 at 7:41 PM
🎉🎉 Big congrats to @archiki.bsky.social on being awarded the @Apple AI/ML PhD Fellowship, for her extensive contributions in evaluating+improving reasoning in language/reward models and their applications to new domains (ReCEval, RepARe, System-1.x, ADaPT, ReGAL, ScPO, UTGen, GrIPS)! #ProudAdvisor
Reposted by Mohit Bansal
We had a blast at the NLP@Michigan Day! Many thanks to our outstanding keynote speakers Parisa Kordjamshidi & @mohitbansal.bsky.social, our fantastic organizers Muhammad Khalifa & Siyang Liu, and all the engaged participants from across campus and beyond. So much positive NLP energy! 💛💙
March 12, 2025 at 4:05 PM
We had a blast at the NLP@Michigan Day! Many thanks to our outstanding keynote speakers Parisa Kordjamshidi & @mohitbansal.bsky.social, our fantastic organizers Muhammad Khalifa & Siyang Liu, and all the engaged participants from across campus and beyond. So much positive NLP energy! 💛💙
Reposted by Mohit Bansal
🚨UPCORE is our new method for balancing unlearning/forgetting with maintaining model performance.
Best part is it works by selecting a coreset from the data rather than changing the model, so it is compatible with any unlearning method, with consistent gains for 3 methods + 2 tasks!
Best part is it works by selecting a coreset from the data rather than changing the model, so it is compatible with any unlearning method, with consistent gains for 3 methods + 2 tasks!
🚨 Introducing UPCORE, to balance deleting info from LLMs with keeping their other capabilities intact.
UPCORE selects a coreset of forget data, leading to a better trade-off across 2 datasets and 3 unlearning methods.
🧵👇
UPCORE selects a coreset of forget data, leading to a better trade-off across 2 datasets and 3 unlearning methods.
🧵👇
February 25, 2025 at 2:33 AM
🚨UPCORE is our new method for balancing unlearning/forgetting with maintaining model performance.
Best part is it works by selecting a coreset from the data rather than changing the model, so it is compatible with any unlearning method, with consistent gains for 3 methods + 2 tasks!
Best part is it works by selecting a coreset from the data rather than changing the model, so it is compatible with any unlearning method, with consistent gains for 3 methods + 2 tasks!
Reposted by Mohit Bansal
🚨 Introducing UPCORE, to balance deleting info from LLMs with keeping their other capabilities intact.
UPCORE selects a coreset of forget data, leading to a better trade-off across 2 datasets and 3 unlearning methods.
🧵👇
UPCORE selects a coreset of forget data, leading to a better trade-off across 2 datasets and 3 unlearning methods.
🧵👇
February 25, 2025 at 2:23 AM
🚨 Introducing UPCORE, to balance deleting info from LLMs with keeping their other capabilities intact.
UPCORE selects a coreset of forget data, leading to a better trade-off across 2 datasets and 3 unlearning methods.
🧵👇
UPCORE selects a coreset of forget data, leading to a better trade-off across 2 datasets and 3 unlearning methods.
🧵👇
🚨 Check out "UTGen & UTDebug" for learning to automatically generate unit tests (i.e., discovering inputs which break your code) and then applying them to debug code with LLMs, with strong gains (>12% pass@1) across multiple models/datasets! (see details in 🧵👇)
1/4
1/4
🚨 Excited to share: "Learning to Generate Unit Tests for Automated Debugging" 🚨
which introduces ✨UTGen and UTDebug✨ for teaching LLMs to generate unit tests (UTs) and debugging code from generated tests.
UTGen+UTDebug yields large gains in debugging (+12% pass@1) & addresses 3 key questions:
🧵👇
which introduces ✨UTGen and UTDebug✨ for teaching LLMs to generate unit tests (UTs) and debugging code from generated tests.
UTGen+UTDebug yields large gains in debugging (+12% pass@1) & addresses 3 key questions:
🧵👇
February 5, 2025 at 6:53 PM
🚨 Check out "UTGen & UTDebug" for learning to automatically generate unit tests (i.e., discovering inputs which break your code) and then applying them to debug code with LLMs, with strong gains (>12% pass@1) across multiple models/datasets! (see details in 🧵👇)
1/4
1/4
Reposted by Mohit Bansal
🚨 Excited to announce UTGen and UTDebug, where we first learn to generate unit tests and then apply them to debugging generated code with LLMs, with strong gains (+12% pass@1) on LLM-based debugging across multiple models/datasets via inf.-time scaling and cross-validation+backtracking!
🧵👇
🧵👇
🚨 Excited to share: "Learning to Generate Unit Tests for Automated Debugging" 🚨
which introduces ✨UTGen and UTDebug✨ for teaching LLMs to generate unit tests (UTs) and debugging code from generated tests.
UTGen+UTDebug yields large gains in debugging (+12% pass@1) & addresses 3 key questions:
🧵👇
which introduces ✨UTGen and UTDebug✨ for teaching LLMs to generate unit tests (UTs) and debugging code from generated tests.
UTGen+UTDebug yields large gains in debugging (+12% pass@1) & addresses 3 key questions:
🧵👇
February 4, 2025 at 7:13 PM
🚨 Excited to announce UTGen and UTDebug, where we first learn to generate unit tests and then apply them to debugging generated code with LLMs, with strong gains (+12% pass@1) on LLM-based debugging across multiple models/datasets via inf.-time scaling and cross-validation+backtracking!
🧵👇
🧵👇
Reposted by Mohit Bansal
🚨 Excited to share: "Learning to Generate Unit Tests for Automated Debugging" 🚨
which introduces ✨UTGen and UTDebug✨ for teaching LLMs to generate unit tests (UTs) and debugging code from generated tests.
UTGen+UTDebug yields large gains in debugging (+12% pass@1) & addresses 3 key questions:
🧵👇
which introduces ✨UTGen and UTDebug✨ for teaching LLMs to generate unit tests (UTs) and debugging code from generated tests.
UTGen+UTDebug yields large gains in debugging (+12% pass@1) & addresses 3 key questions:
🧵👇
February 4, 2025 at 7:10 PM
🚨 Excited to share: "Learning to Generate Unit Tests for Automated Debugging" 🚨
which introduces ✨UTGen and UTDebug✨ for teaching LLMs to generate unit tests (UTs) and debugging code from generated tests.
UTGen+UTDebug yields large gains in debugging (+12% pass@1) & addresses 3 key questions:
🧵👇
which introduces ✨UTGen and UTDebug✨ for teaching LLMs to generate unit tests (UTs) and debugging code from generated tests.
UTGen+UTDebug yields large gains in debugging (+12% pass@1) & addresses 3 key questions:
🧵👇
🎉 Congrats to the awesome students, postdocs, & collaborators for this exciting batch of #ICLR2025 and #NAACL2025 accepted papers (FYI some are on the academic/industry job market and a great catch 🙂), on diverse, important topics such as:
-- adaptive data generation environments/policies
...
🧵
-- adaptive data generation environments/policies
...
🧵
January 27, 2025 at 9:38 PM
🎉 Congrats to the awesome students, postdocs, & collaborators for this exciting batch of #ICLR2025 and #NAACL2025 accepted papers (FYI some are on the academic/industry job market and a great catch 🙂), on diverse, important topics such as:
-- adaptive data generation environments/policies
...
🧵
-- adaptive data generation environments/policies
...
🧵
Reposted by Mohit Bansal
🎉Very excited that our work on Persuasion-Balanced Training has been accepted to #NAACL2025! We introduce a multi-agent tree-based method for teaching models to balance:
1️⃣ Accepting persuasion when it helps
2️⃣ Resisting persuasion when it hurts (e.g. misinformation)
arxiv.org/abs/2410.14596
🧵 1/4
1️⃣ Accepting persuasion when it helps
2️⃣ Resisting persuasion when it hurts (e.g. misinformation)
arxiv.org/abs/2410.14596
🧵 1/4
January 23, 2025 at 4:51 PM
🎉Very excited that our work on Persuasion-Balanced Training has been accepted to #NAACL2025! We introduce a multi-agent tree-based method for teaching models to balance:
1️⃣ Accepting persuasion when it helps
2️⃣ Resisting persuasion when it hurts (e.g. misinformation)
arxiv.org/abs/2410.14596
🧵 1/4
1️⃣ Accepting persuasion when it helps
2️⃣ Resisting persuasion when it hurts (e.g. misinformation)
arxiv.org/abs/2410.14596
🧵 1/4